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

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

Neuron 4601 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0287. Min Act: -0.0003

Data Index: 105047 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1283791 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0257. Min Act: -0.0003

Data Index: 788880 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0250. Min Act: -0.0003

Data Index: 848507 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0239. Min Act: -0.0003

Data Index: 982805 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0245. Min Act: -0.0003

Data Index: 958033 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0243. Min Act: -0.0003

Data Index: 215722 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1095013 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0232. Min Act: -0.0003

Data Index: 573136 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0235. Min Act: -0.0003

Data Index: 370298 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1167257 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0231. Min Act: -0.0003

Data Index: 152824 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0222. Min Act: -0.0003

Data Index: 483957 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1131320 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0218. Min Act: -0.0003

Data Index: 629022 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1145196 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0216. Min Act: -0.0003

Data Index: 532344 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0220. Min Act: -0.0003

Data Index: 244920 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1194884 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0213. Min Act: -0.0003

Data Index: 888551 (C4 (Web Text))

Max Activating Token Index: 549