Re:We Found an Neuron in GPT-2
by hackinthebochs on Friday February 17, 2023 @07:51PM
(#34842693)
>so there's some kind of plan and execute going on. maybe it can do that in model some how
The simple answer is that the internal state that picks the next token is stable over iterations so that the model can follow a consistent plan over multiple token outputs. Then as the plan "unfolds" in the output tokens, these tokens help stabilize the plan further, thus creating consistency over long generations.
The simple answer is that the internal state that picks the next token is stable over iterations so that the model can follow a consistent plan over multiple token outputs. Then as the plan "unfolds" in the output tokens, these tokens help stabilize the plan further, thus creating consistency over long generations.