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

Dataset: The Pile

Neuron 536 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: 1.5237. Min Range: -1.5237

Max Act: 1.5237. Min Act: -0.0000

Data Index: 1448917 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1839683 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.3978. Min Act: -0.0000

Data Index: 265566 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.3131. Min Act: -0.0000

Data Index: 892059 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1960944 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.3539. Min Act: -0.0000

Data Index: 681473 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1867847 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.2391. Min Act: -0.0000

Data Index: 48913 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1285. Min Act: -0.0000

Data Index: 478920 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1996. Min Act: -0.0000

Data Index: 466315 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0291. Min Act: -0.0000

Data Index: 1973333 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1762. Min Act: -0.0000

Data Index: 1339644 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1543423 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0909. Min Act: -0.0000

Data Index: 937559 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1201680 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1839018 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1380. Min Act: -0.0000

Data Index: 348378 (The Pile)

Max Activating Token Index: 591

Text #17

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0950. Min Act: -0.0000

Data Index: 249829 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1105437 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0468. Min Act: -0.0000

Data Index: 280319 (The Pile)

Max Activating Token Index: 377