Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 777 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.4026. Min Act: -0.0000

Data Index: 147569 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.1915. Min Act: -0.0000

Data Index: 895184 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1231218 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1755972 (The Pile)

Max Activating Token Index: 406

Text #4

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.1999. Min Act: -0.0000

Data Index: 914704 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.3173. Min Act: -0.0000

Data Index: 894123 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0841. Min Act: -0.0000

Data Index: 198425 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1574793 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1899080 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0924. Min Act: -0.0000

Data Index: 23780 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1594633 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0678. Min Act: -0.0000

Data Index: 987413 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0621. Min Act: -0.0000

Data Index: 13160 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1137125 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1887224 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.9755. Min Act: -0.0000

Data Index: 839660 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1199211 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1497268 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1377750 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1701385 (The Pile)

Max Activating Token Index: 574