Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4320 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0232. Min Act: -0.0003

Data Index: 416423 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1210064 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0003

Data Index: 255488 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0205. Min Act: -0.0003

Data Index: 146579 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0211. Min Act: -0.0002

Data Index: 655640 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1206505 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0209. Min Act: -0.0003

Data Index: 838683 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0201. Min Act: -0.0003

Data Index: 81242 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0212. Min Act: -0.0003

Data Index: 213895 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0221. Min Act: -0.0003

Data Index: 669530 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0207. Min Act: -0.0003

Data Index: 559258 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1432422 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1111389 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0217. Min Act: -0.0003

Data Index: 587799 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0234. Min Act: -0.0003

Data Index: 632657 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0207. Min Act: -0.0002

Data Index: 909469 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0199. Min Act: -0.0003

Data Index: 300443 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0215. Min Act: -0.0003

Data Index: 35657 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0223. Min Act: -0.0003

Data Index: 371308 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0226. Min Act: -0.0003

Data Index: 213358 (C4 (Web Text))

Max Activating Token Index: 241