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

Dataset: The Pile

Neuron 1532 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6623. Min Act: -0.0000

Data Index: 900310 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1515339 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1501387 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5768. Min Act: -0.0000

Data Index: 30228 (The Pile)

Max Activating Token Index: 43

Text #4

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1406096 (The Pile)

Max Activating Token Index: 840

Text #5

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5730. Min Act: -0.0000

Data Index: 5963 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5523. Min Act: -0.0000

Data Index: 888907 (The Pile)

Max Activating Token Index: 801

Text #7

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1425593 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5179. Min Act: -0.0000

Data Index: 303508 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1726072 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1975244 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1437630 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1960250 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1487808 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5144. Min Act: -0.0000

Data Index: 28054 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1900862 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1223267 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1002611 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1853899 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5625. Min Act: -0.0000

Data Index: 505705 (The Pile)

Max Activating Token Index: 769