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

Dataset: The Pile

Neuron 605 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: 0.5148. Min Range: -0.5148

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1401324 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1971162 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4330. Min Act: -0.0000

Data Index: 143115 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1345268 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3617. Min Act: -0.0000

Data Index: 370639 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1805391 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3909. Min Act: -0.0000

Data Index: 10012 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1159732 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3824. Min Act: -0.0000

Data Index: 845667 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3643. Min Act: -0.0000

Data Index: 26988 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1474024 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1352027 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3632. Min Act: -0.0000

Data Index: 220140 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1475167 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1607954 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3330. Min Act: -0.0000

Data Index: 584785 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3328. Min Act: -0.0000

Data Index: 517167 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3020. Min Act: -0.0000

Data Index: 816773 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1195335 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1353547 (The Pile)

Max Activating Token Index: 180