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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3629 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1312815 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0339. Min Act: -0.0001

Data Index: 241230 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0350. Min Act: -0.0001

Data Index: 687414 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0344. Min Act: -0.0001

Data Index: 41187 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0343. Min Act: -0.0001

Data Index: 108894 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0319. Min Act: -0.0001

Data Index: 354848 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1158474 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0315. Min Act: -0.0001

Data Index: 852971 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0322. Min Act: -0.0001

Data Index: 685458 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0328. Min Act: -0.0001

Data Index: 733889 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0329. Min Act: -0.0001

Data Index: 752144 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0318. Min Act: -0.0001

Data Index: 389364 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1086189 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0303. Min Act: -0.0001

Data Index: 707126 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0319. Min Act: -0.0001

Data Index: 177662 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0273. Min Act: -0.0001

Data Index: 346319 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0286. Min Act: -0.0001

Data Index: 743545 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1172171 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0303. Min Act: -0.0001

Data Index: 963629 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0236. Min Act: -0.0001

Data Index: 4934 (C4 (Web Text))

Max Activating Token Index: 834