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

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

Neuron 678 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0302. Min Act: -0.0002

Data Index: 734450 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0290. Min Act: -0.0002

Data Index: 143193 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0291. Min Act: -0.0002

Data Index: 234660 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1085411 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1074909 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0256. Min Act: -0.0002

Data Index: 183906 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1305044 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0256. Min Act: -0.0002

Data Index: 958104 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1008872 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1001967 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0281. Min Act: -0.0002

Data Index: 915294 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1630281 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0262. Min Act: -0.0002

Data Index: 871997 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0248. Min Act: -0.0002

Data Index: 972364 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0236. Min Act: -0.0002

Data Index: 333546 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0255. Min Act: -0.0002

Data Index: 228752 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0228. Min Act: -0.0002

Data Index: 968889 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0241. Min Act: -0.0002

Data Index: 577377 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1096134 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0231. Min Act: -0.0002

Data Index: 574182 (C4 (Web Text))

Max Activating Token Index: 393