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

Dataset: The Pile

Neuron 3041 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.5245. Min Act: -0.0000

Data Index: 1823525 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.6279. Min Act: -0.0000

Data Index: 1615421 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.5339. Min Act: -0.0000

Data Index: 185730 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.5160. Min Act: -0.0000

Data Index: 1704164 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1215681 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.4185. Min Act: -0.0000

Data Index: 812524 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1602577 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2740. Min Act: -0.0000

Data Index: 113334 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1611991 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.4838. Min Act: -0.0000

Data Index: 859183 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1126048 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2360. Min Act: -0.0000

Data Index: 1838865 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1472872 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3166. Min Act: -0.0000

Data Index: 1699036 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2279. Min Act: -0.0000

Data Index: 534574 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3099. Min Act: -0.0000

Data Index: 635105 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1496501 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1087456 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.1760. Min Act: -0.0000

Data Index: 219291 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3811. Min Act: -0.0000

Data Index: 13185 (The Pile)

Max Activating Token Index: 976