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

Dataset: The Pile

Neuron 3318 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1179611 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1397985 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1348211 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5022. Min Act: -0.0000

Data Index: 209209 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4827. Min Act: -0.0000

Data Index: 955845 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1337868 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4791. Min Act: 0.0000

Data Index: 1689635 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1621715 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1264984 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1841514 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4033. Min Act: -0.0000

Data Index: 374748 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1246228 (The Pile)

Max Activating Token Index: 832

Text #12

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1231069 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4285. Min Act: -0.0000

Data Index: 106502 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4213. Min Act: -0.0000

Data Index: 484876 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1997829 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1493178 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3443. Min Act: -0.0000

Data Index: 26161 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1056526 (The Pile)

Max Activating Token Index: 450

Text #19

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3842. Min Act: -0.0000

Data Index: 504514 (The Pile)

Max Activating Token Index: 67