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

Dataset: The Pile

Neuron 76 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: 0.7815. Min Range: -0.7815

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1198462 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1151460 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7635. Min Act: -0.0000

Data Index: 470366 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7228. Min Act: -0.0000

Data Index: 260213 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1139376 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7195. Min Act: -0.0000

Data Index: 507297 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1888571 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7222. Min Act: -0.0000

Data Index: 782429 (The Pile)

Max Activating Token Index: 408

Text #8

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7140. Min Act: -0.0000

Data Index: 814431 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6653. Min Act: -0.0000

Data Index: 461679 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6749. Min Act: -0.0000

Data Index: 831289 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1874055 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6948. Min Act: -0.0000

Data Index: 800773 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1140303 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6043. Min Act: -0.0000

Data Index: 335575 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7194. Min Act: -0.0000

Data Index: 748572 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1317927 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6428. Min Act: -0.0000

Data Index: 620145 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1343277 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1564226 (The Pile)

Max Activating Token Index: 383