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

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

Neuron 677 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: 0.0001

Data Index: 357971 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0257. Min Act: 0.0001

Data Index: 237398 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0257. Min Act: 0.0001

Data Index: 351744 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0253. Min Act: 0.0004

Data Index: 999206 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0253. Min Act: 0.0000

Data Index: 1068589 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0245. Min Act: 0.0001

Data Index: 1112440 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0249. Min Act: -0.0000

Data Index: 1234491 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0255. Min Act: 0.0000

Data Index: 671381 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0246. Min Act: -0.0000

Data Index: 97621 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0246. Min Act: 0.0000

Data Index: 942742 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0253. Min Act: 0.0003

Data Index: 1019308 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0235. Min Act: -0.0000

Data Index: 463665 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0242. Min Act: 0.0001

Data Index: 538703 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0235. Min Act: 0.0003

Data Index: 636816 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0231. Min Act: -0.0000

Data Index: 571533 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0237. Min Act: 0.0000

Data Index: 739598 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0238. Min Act: -0.0000

Data Index: 746902 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0226. Min Act: 0.0000

Data Index: 1556678 (Python Code)

Max Activating Token Index: 947

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0244. Min Act: 0.0000

Data Index: 460896 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0235. Min Act: 0.0001

Data Index: 663188 (C4 (Web Text))

Max Activating Token Index: 384