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

Dataset: The Pile

Neuron 1968 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.5235. Min Act: -0.0000

Data Index: 770179 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.5892. Min Act: -0.0000

Data Index: 1283808 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.0959. Min Act: -0.0000

Data Index: 1463794 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.0626. Min Act: -0.0000

Data Index: 616749 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.1057. Min Act: -0.0000

Data Index: 422367 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3493. Min Act: -0.0000

Data Index: 595096 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.9644. Min Act: -0.0000

Data Index: 217776 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.8409. Min Act: -0.0000

Data Index: 1515682 (The Pile)

Max Activating Token Index: 165

Text #8

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.1945. Min Act: -0.0000

Data Index: 2106 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.7039. Min Act: -0.0000

Data Index: 447058 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.8392. Min Act: -0.0000

Data Index: 713951 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.9247. Min Act: -0.0000

Data Index: 1931552 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.8662. Min Act: -0.0000

Data Index: 1461993 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.7548. Min Act: -0.0000

Data Index: 144300 (The Pile)

Max Activating Token Index: 69

Text #14

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.2606. Min Act: -0.0000

Data Index: 1167404 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.8498. Min Act: -0.0000

Data Index: 691710 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.7413. Min Act: -0.0000

Data Index: 896751 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.5754. Min Act: -0.0000

Data Index: 219773 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.8293. Min Act: -0.0000

Data Index: 1505836 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 3.5892. Min Range: -3.5892

Max Act: 2.7496. Min Act: -0.0000

Data Index: 1094823 (The Pile)

Max Activating Token Index: 483