Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3447 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.3243. Min Act: -0.0000

Data Index: 1606717 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.2414. Min Act: -0.0000

Data Index: 139863 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.1780. Min Act: -0.0000

Data Index: 638642 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.1531. Min Act: -0.0000

Data Index: 960594 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1580245 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.0746. Min Act: -0.0000

Data Index: 404736 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.0423. Min Act: -0.0000

Data Index: 1561165 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9759. Min Act: -0.0000

Data Index: 875759 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.0111. Min Act: -0.0000

Data Index: 40150 (The Pile)

Max Activating Token Index: 403

Text #9

Max Range: 1.3243. Min Range: -1.3243

Max Act: 1.0349. Min Act: -0.0000

Data Index: 870816 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9532. Min Act: -0.0001

Data Index: 435553 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1006123 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1935374 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1107291 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1649583 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1437934 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9050. Min Act: -0.0000

Data Index: 662049 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9056. Min Act: -0.0000

Data Index: 868328 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.8943. Min Act: -0.0000

Data Index: 679112 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 1.3243. Min Range: -1.3243

Max Act: 0.9193. Min Act: -0.0000

Data Index: 616101 (The Pile)

Max Activating Token Index: 588