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

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

Neuron 36 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: 0.2205. Min Range: -0.2205

Max Act: 0.2205. Min Act: -0.0002

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1312020 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0296. Min Act: -0.0002

Data Index: 684833 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0318. Min Act: -0.0002

Data Index: 289233 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1061812 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0312. Min Act: -0.0002

Data Index: 583273 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0289. Min Act: -0.0002

Data Index: 143569 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0278. Min Act: -0.0002

Data Index: 881438 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0265. Min Act: -0.0002

Data Index: 191173 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0251. Min Act: -0.0002

Data Index: 432936 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0241. Min Act: -0.0002

Data Index: 577681 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0241. Min Act: -0.0002

Data Index: 405362 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0246. Min Act: -0.0002

Data Index: 261669 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1283442 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0220. Min Act: -0.0002

Data Index: 854893 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1132138 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0249. Min Act: -0.0002

Data Index: 105084 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0255. Min Act: -0.0002

Data Index: 270311 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1344206 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1345468 (C4 (Web Text))

Max Activating Token Index: 805