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

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

Neuron 613 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0001

Data Index: 406764 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0274. Min Act: -0.0001

Data Index: 829977 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0251. Min Act: -0.0001

Data Index: 641811 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1043902 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0223. Min Act: -0.0001

Data Index: 417728 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0212. Min Act: -0.0001

Data Index: 27653 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1034458 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0212. Min Act: -0.0001

Data Index: 217855 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0218. Min Act: -0.0001

Data Index: 626801 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0223. Min Act: -0.0001

Data Index: 828636 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0205. Min Act: -0.0001

Data Index: 45721 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0207. Min Act: -0.0001

Data Index: 68624 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0195. Min Act: -0.0001

Data Index: 40624 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1312258 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1110903 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0202. Min Act: -0.0001

Data Index: 166895 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0203. Min Act: -0.0001

Data Index: 79224 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1325963 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0195. Min Act: -0.0001

Data Index: 425244 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0195. Min Act: -0.0001

Data Index: 851764 (C4 (Web Text))

Max Activating Token Index: 720