Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4895 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1031788 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6907. Min Act: -0.0000

Data Index: 366702 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1132451 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1684577 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1284620 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7043. Min Act: -0.0000

Data Index: 208629 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5574. Min Act: -0.0000

Data Index: 779841 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6937. Min Act: -0.0000

Data Index: 277515 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1744923 (The Pile)

Max Activating Token Index: 672

Text #9

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1664229 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5757. Min Act: -0.0000

Data Index: 36424 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6164. Min Act: -0.0000

Data Index: 587834 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1155554 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1250555 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1532043 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5849. Min Act: -0.0000

Data Index: 325525 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5468. Min Act: -0.0000

Data Index: 817878 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1435160 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5942. Min Act: -0.0000

Data Index: 939603 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6731. Min Act: -0.0000

Data Index: 966799 (The Pile)

Max Activating Token Index: 674