Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1641 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0005

Data Index: 1187874 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0005

Data Index: 801313 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0240. Min Act: -0.0005

Data Index: 281292 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0250. Min Act: -0.0005

Data Index: 513223 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0235. Min Act: -0.0005

Data Index: 418200 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0228. Min Act: -0.0005

Data Index: 533648 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0217. Min Act: -0.0005

Data Index: 1355453 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0226. Min Act: -0.0005

Data Index: 962411 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0243. Min Act: -0.0005

Data Index: 996136 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0217. Min Act: -0.0005

Data Index: 101525 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0219. Min Act: -0.0005

Data Index: 59432 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0242. Min Act: -0.0005

Data Index: 584811 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0186. Min Act: -0.0005

Data Index: 798487 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0224. Min Act: -0.0005

Data Index: 64371 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0215. Min Act: -0.0005

Data Index: 926680 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0219. Min Act: -0.0005

Data Index: 799941 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0214. Min Act: -0.0005

Data Index: 751470 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0213. Min Act: -0.0005

Data Index: 387599 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0214. Min Act: -0.0005

Data Index: 956900 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0199. Min Act: -0.0005

Data Index: 237867 (C4 (Web Text))

Max Activating Token Index: 213