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

Dataset: The Pile

Neuron 3371 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: 1.4363. Min Range: -1.4363

Max Act: 1.4363. Min Act: -0.0000

Data Index: 1799336 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1766877 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.1931. Min Act: -0.0000

Data Index: 583639 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.2315. Min Act: -0.0000

Data Index: 661435 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.2501. Min Act: -0.0000

Data Index: 636982 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1011538 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1163913 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.0799. Min Act: -0.0000

Data Index: 141822 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.0751. Min Act: -0.0000

Data Index: 672727 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1435860 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.9706. Min Act: -0.0000

Data Index: 662941 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.9888. Min Act: -0.0000

Data Index: 935324 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1577744 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 1.4363. Min Range: -1.4363

Max Act: 1.0118. Min Act: -0.0000

Data Index: 980143 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.9707. Min Act: -0.0000

Data Index: 865244 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.9817. Min Act: -0.0000

Data Index: 399842 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.8701. Min Act: -0.0000

Data Index: 183784 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.9419. Min Act: -0.0000

Data Index: 889454 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.8467. Min Act: -0.0000

Data Index: 228624 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 1.4363. Min Range: -1.4363

Max Act: 0.8996. Min Act: -0.0000

Data Index: 743070 (The Pile)

Max Activating Token Index: 941