Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3955 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0003

Data Index: 392156 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0243. Min Act: -0.0003

Data Index: 111439 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0208. Min Act: -0.0003

Data Index: 168823 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1029803 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0228. Min Act: -0.0003

Data Index: 56397 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0227. Min Act: -0.0003

Data Index: 943471 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0211. Min Act: -0.0003

Data Index: 461365 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0003

Data Index: 935287 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0217. Min Act: -0.0003

Data Index: 836567 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0209. Min Act: -0.0003

Data Index: 783991 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0003

Data Index: 798204 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0191. Min Act: -0.0003

Data Index: 736157 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0209. Min Act: -0.0003

Data Index: 183385 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1133982 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0196. Min Act: -0.0003

Data Index: 101120 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0184. Min Act: -0.0003

Data Index: 606247 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0189. Min Act: -0.0003

Data Index: 964937 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0194. Min Act: -0.0003

Data Index: 482906 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1107238 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0187. Min Act: -0.0003

Data Index: 872195 (C4 (Web Text))

Max Activating Token Index: 586