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

Dataset: The Pile

Neuron 2643 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: 3.2665. Min Range: -3.2665

Max Act: 3.2665. Min Act: -0.0000

Data Index: 122345 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1210. Min Act: -0.0000

Data Index: 219835 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9245. Min Act: -0.0000

Data Index: 1581927 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.6923. Min Act: -0.0000

Data Index: 438148 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.7966. Min Act: -0.0000

Data Index: 1867970 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.7836. Min Act: -0.0000

Data Index: 1136769 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9191. Min Act: -0.0000

Data Index: 1216243 (The Pile)

Max Activating Token Index: 826

Text #7

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.6425. Min Act: -0.0000

Data Index: 910327 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.5092. Min Act: -0.0000

Data Index: 731600 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.5929. Min Act: -0.0000

Data Index: 1013247 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.7306. Min Act: -0.0000

Data Index: 947635 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.8282. Min Act: -0.0000

Data Index: 762538 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.8308. Min Act: -0.0000

Data Index: 906025 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.6977. Min Act: -0.0000

Data Index: 663571 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.3959. Min Act: -0.0000

Data Index: 917656 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.5711. Min Act: -0.0000

Data Index: 457878 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.6526. Min Act: -0.0000

Data Index: 907015 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.3768. Min Act: -0.0000

Data Index: 1900444 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.7812. Min Act: -0.0000

Data Index: 27253 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.4762. Min Act: -0.0000

Data Index: 359650 (The Pile)

Max Activating Token Index: 168