Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers

Trained transformers reliably develop massive activations, a small number of hidden dimensions whose magnitude is far above the median and which concentrate on the sequence-start token. Whether these outliers are a removable artifact of the residual stream's overloaded read and write role, or instead a functional necessity, is actively debated. We test the artifact hypothesis directly, with an architectural intervention. Our architecture, Ledger Residuals, splits the residual stream into a mutable scratch stream (Deliberation) that intermediate computation may freely overwrite and a protected, decode-only accumulator (Commitment) that holds the representation the model reads out. If massive activations exist only because one stream is forced to be both scratchpad and answer, then a dedicated answer channel should remove the need for them. We find that it does not. In matched-loss language models at the 160M and 290M scales, the model rebuilds the canonical fixed-dimension, start-token outlier inside the protected channel. The rebuilt feature is smaller in magnitude than in a standard transformer but more sharply concentrated on the start token, and a stronger sparsity penalty makes it more persistent and more concentrated still, rather than removing it. Massive activations therefore look architecturally robust: they re-emerge in whichever representation the model decodes from, which is what we would expect if they are functional rather than incidental. We release our architecture and measurement code.

Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal structure remains difficult to interpret due to the additive superposition induced by the residual stream. We examine whether the activation of an FFN neuron can be explained by a sparse set of preceding neuron activations and attention outputs. We introduce a training-free attribution method that estimates the relative influence of upstream neurons and attention outputs on a target neuron's activation. Empirically, across models and layers, we find that small subsets of preceding activations and attention outputs suffice to preserve neuron activations with high fidelity when all remaining inputs are masked with their average values. Effective sparsity is even greater when accounting for the inherent activation sparsity of upstream layers. Moreover, applying the neuron-specific masks in all layers simultaneously, such that the induced deviations propagate through the network, leaves model perplexity largely unchanged at moderate sparsity levels. These results demonstrate that, despite dense parameterization, FFNs exhibit sparse and structured inter-layer dependencies at the neuron level. Our method provides a practical, scalable tool for circuit-level interpretability and identifies candidate sparse pathways with potential implications for efficient inference.

A transformer can be built from operators that are legible by construction -- bounded, named units that read as fuzzy set operations rather than dense activations -- but legibility must be pressed for during training, and the pressure has a failure mode. A crispness penalty meant to sharpen a bounded operator into a decisive detector instead collapses it into a dead constant. An identity, E[v(1-v)] = mu(1-mu) - var, shows why -- the penalty is a variance-minimizer blind to the difference between a live detector and a constant -- and names the fix: a per-channel variance floor, the target legibility metric written as a loss, which recovers both legibility and quality. A learned per-unit fraction then retires the hand-set reserved-GELU partition of prior work: given the choice the model keeps no unit as pure GELU and routes 87% of its load-bearing computation through crisp operators. The result is the most legible transformer we have built -- 78% of its feed-forward operands and 50% of its attention value channels are crisp-and-contextual detectors, and per-head legibility rises from 18% in shallow layers to 78% in deep ones. Read in the correct rotated per-layer frame, these units separate a clean detection (what a unit responds to) from a harder naming (what its output decodes to); and because the objective makes each unit crisp and sparse, edits to them are far more local -- 50-184x in the deep layers where the edit sites concentrate -- and can target explicit conjunctions a single neuron cannot express. Finally, a between-unit decorrelation pressure exposes a legibility dial: it trades a circuit's reuse for independence at no quality cost, turning concepts into single, surgically editable units and a prediction into a short explanation read off a handful of named operations. Quality holds at parity with a conventional baseline throughout.