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

Dataset: The Pile

Neuron 2035 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1688933 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2330. Min Act: -0.0000

Data Index: 773321 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2207. Min Act: -0.0000

Data Index: 579194 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1624. Min Act: -0.0000

Data Index: 47539 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1155. Min Act: -0.0000

Data Index: 163730 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1116. Min Act: -0.0000

Data Index: 245340 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1710397 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1183455 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1734983 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.9732. Min Act: -0.0000

Data Index: 89281 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8992. Min Act: -0.0000

Data Index: 453979 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1959521 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1739588 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8928. Min Act: -0.0000

Data Index: 819201 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8111. Min Act: -0.0000

Data Index: 950441 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8251. Min Act: -0.0000

Data Index: 956231 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1762398 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1918613 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1018561 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1889483 (The Pile)

Max Activating Token Index: 387