Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 95 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0227. Min Act: -0.0006

Data Index: 445372 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0242. Min Act: -0.0006

Data Index: 201723 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0231. Min Act: -0.0006

Data Index: 623831 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0240. Min Act: -0.0006

Data Index: 949119 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0243. Min Act: -0.0006

Data Index: 172351 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0224. Min Act: -0.0006

Data Index: 750238 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0219. Min Act: -0.0006

Data Index: 546396 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0232. Min Act: -0.0006

Data Index: 176303 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1353982 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0222. Min Act: -0.0006

Data Index: 216845 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0221. Min Act: -0.0006

Data Index: 937885 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0217. Min Act: -0.0006

Data Index: 468825 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0221. Min Act: -0.0006

Data Index: 447952 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0220. Min Act: -0.0006

Data Index: 204477 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0218. Min Act: -0.0006

Data Index: 864034 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0221. Min Act: -0.0005

Data Index: 45428 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0205. Min Act: -0.0005

Data Index: 605871 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0215. Min Act: -0.0006

Data Index: 550659 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1055241 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0229. Min Act: -0.0006

Data Index: 173701 (C4 (Web Text))

Max Activating Token Index: 651