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

Dataset: The Pile

Neuron 3298 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1277501 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4361. Min Act: -0.0000

Data Index: 488215 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4550. Min Act: -0.0000

Data Index: 966562 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4618. Min Act: -0.0000

Data Index: 142720 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4221. Min Act: -0.0000

Data Index: 368983 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3913. Min Act: -0.0000

Data Index: 309553 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1594811 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1307402 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3567. Min Act: -0.0000

Data Index: 102741 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3668. Min Act: -0.0000

Data Index: 516287 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1632441 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1041435 (The Pile)

Max Activating Token Index: 912

Text #12

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3199. Min Act: -0.0000

Data Index: 214044 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1900581 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3471. Min Act: -0.0000

Data Index: 802255 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1046264 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1950957 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3404. Min Act: -0.0000

Data Index: 907875 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1184714 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3481. Min Act: -0.0000

Data Index: 886358 (The Pile)

Max Activating Token Index: 21