Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1481 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0003

Data Index: 101509 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0270. Min Act: -0.0003

Data Index: 938463 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0247. Min Act: -0.0003

Data Index: 936495 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1283758 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0242. Min Act: -0.0003

Data Index: 427853 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0252. Min Act: -0.0003

Data Index: 157782 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1213275 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0243. Min Act: -0.0003

Data Index: 512914 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0242. Min Act: -0.0003

Data Index: 822324 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0223. Min Act: -0.0003

Data Index: 46942 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0231. Min Act: -0.0003

Data Index: 286250 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0231. Min Act: -0.0003

Data Index: 512157 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0222. Min Act: -0.0003

Data Index: 45923 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1033304 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0208. Min Act: -0.0003

Data Index: 685251 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0213. Min Act: -0.0003

Data Index: 793930 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0226. Min Act: -0.0002

Data Index: 33367 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1289639 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0216. Min Act: -0.0003

Data Index: 308660 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0215. Min Act: -0.0003

Data Index: 913469 (C4 (Web Text))

Max Activating Token Index: 143