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

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

Neuron 82 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0291. Min Act: -0.0003

Data Index: 33522 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0256. Min Act: -0.0004

Data Index: 31980 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1325265 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0250. Min Act: -0.0004

Data Index: 638689 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0250. Min Act: -0.0004

Data Index: 904066 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0243. Min Act: -0.0003

Data Index: 333361 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0247. Min Act: -0.0004

Data Index: 977384 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0241. Min Act: -0.0004

Data Index: 972643 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0228. Min Act: -0.0003

Data Index: 311364 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0226. Min Act: -0.0003

Data Index: 677661 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0223. Min Act: -0.0003

Data Index: 786872 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0227. Min Act: -0.0003

Data Index: 569015 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1172661 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0231. Min Act: -0.0003

Data Index: 165481 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1244253 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1248551 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1178988 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0223. Min Act: -0.0004

Data Index: 888961 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0235. Min Act: -0.0004

Data Index: 492742 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0223. Min Act: -0.0003

Data Index: 314909 (C4 (Web Text))

Max Activating Token Index: 855