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

Dataset: The Pile

Neuron 1308 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: 0.9162. Min Range: -0.9162

Max Act: 0.9162. Min Act: -0.0000

Data Index: 787921 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1426329 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.9025. Min Act: -0.0000

Data Index: 474837 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.8557. Min Act: -0.0000

Data Index: 608578 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7891. Min Act: -0.0000

Data Index: 625035 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.8407. Min Act: -0.0000

Data Index: 682576 (The Pile)

Max Activating Token Index: 430

Text #6

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1980059 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.8582. Min Act: -0.0000

Data Index: 183985 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1665798 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1987084 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.8021. Min Act: -0.0000

Data Index: 135371 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1855158 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1167960 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7537. Min Act: -0.0000

Data Index: 494866 (The Pile)

Max Activating Token Index: 282

Text #14

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7030. Min Act: -0.0000

Data Index: 339094 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7239. Min Act: -0.0000

Data Index: 377593 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1063771 (The Pile)

Max Activating Token Index: 26

Text #17

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1358420 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1710324 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 0.9162. Min Range: -0.9162

Max Act: 0.7373. Min Act: -0.0000

Data Index: 571450 (The Pile)

Max Activating Token Index: 353