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

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

Neuron 39 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: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1602161 (Python Code)

Max Activating Token Index: 832

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1316823 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0236. Min Act: -0.0003

Data Index: 738351 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0240. Min Act: -0.0003

Data Index: 974066 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0239. Min Act: -0.0003

Data Index: 505650 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0237. Min Act: -0.0003

Data Index: 781450 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0227. Min Act: -0.0003

Data Index: 538105 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0235. Min Act: -0.0003

Data Index: 429143 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1373188 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0232. Min Act: -0.0003

Data Index: 536640 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1437942 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1155125 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1044045 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0224. Min Act: -0.0003

Data Index: 575097 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0225. Min Act: -0.0003

Data Index: 185312 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0217. Min Act: -0.0003

Data Index: 477940 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1504059 (Python Code)

Max Activating Token Index: 186

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0220. Min Act: -0.0003

Data Index: 160616 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1394072 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0212. Min Act: -0.0003

Data Index: 86254 (C4 (Web Text))

Max Activating Token Index: 641