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

Dataset: The Pile

Neuron 2353 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7805. Min Act: -0.0000

Data Index: 616939 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1467555 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1856460 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6805. Min Act: -0.0000

Data Index: 572791 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7190. Min Act: -0.0000

Data Index: 757599 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1012325 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7076. Min Act: -0.0000

Data Index: 291788 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1488620 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1012247 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1329382 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6878. Min Act: -0.0000

Data Index: 513182 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6483. Min Act: -0.0000

Data Index: 432136 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6673. Min Act: -0.0000

Data Index: 880072 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1409258 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1121853 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6518. Min Act: -0.0000

Data Index: 533417 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1322911 (The Pile)

Max Activating Token Index: 405

Text #17

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1919036 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6678. Min Act: -0.0000

Data Index: 145861 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6426. Min Act: -0.0000

Data Index: 179147 (The Pile)

Max Activating Token Index: 130