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

Dataset: The Pile

Neuron 42 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: 0.3932. Min Range: -0.3932

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1412248 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3932. Min Act: -0.0000

Data Index: 894198 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1190510 (The Pile)

Max Activating Token Index: 529

Text #3

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1839566 (The Pile)

Max Activating Token Index: 346

Text #4

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3397. Min Act: 0.0000

Data Index: 1373299 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3039. Min Act: -0.0000

Data Index: 584560 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1846997 (The Pile)

Max Activating Token Index: 556

Text #7

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1479277 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1606567 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1532143 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3027. Min Act: -0.0000

Data Index: 218408 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1229964 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2946. Min Act: -0.0000

Data Index: 861647 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1098479 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1286723 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2911. Min Act: -0.0000

Data Index: 388342 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2893. Min Act: -0.0000

Data Index: 136663 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1603037 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2858. Min Act: 0.0000

Data Index: 579529 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2813. Min Act: 0.0000

Data Index: 62617 (The Pile)

Max Activating Token Index: 791