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

Dataset: The Pile

Neuron 4603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1603656 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1162081 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1006204 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1461321 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4809. Min Act: -0.0000

Data Index: 998348 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1992733 (The Pile)

Max Activating Token Index: 802

Text #6

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.5272. Min Act: -0.0000

Data Index: 57415 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1752725 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4458. Min Act: -0.0000

Data Index: 32441 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1249259 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4507. Min Act: -0.0000

Data Index: 663083 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1907008 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4347. Min Act: -0.0000

Data Index: 886418 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4285. Min Act: -0.0000

Data Index: 360425 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1044288 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1020449 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1761917 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1512269 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4491. Min Act: -0.0000

Data Index: 690578 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.8929. Min Range: -0.8929

Max Act: 0.4037. Min Act: -0.0000

Data Index: 840994 (The Pile)

Max Activating Token Index: 730