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

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

Neuron 4693 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: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0003

Data Index: 748862 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0273. Min Act: -0.0002

Data Index: 667853 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0258. Min Act: -0.0003

Data Index: 362950 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1132015 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1279267 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0234. Min Act: -0.0002

Data Index: 60041 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0238. Min Act: -0.0002

Data Index: 223441 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0236. Min Act: -0.0003

Data Index: 586273 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1214759 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1005600 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0221. Min Act: -0.0003

Data Index: 961014 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0227. Min Act: -0.0002

Data Index: 883606 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1154996 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1551888 (Python Code)

Max Activating Token Index: 595

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0225. Min Act: -0.0002

Data Index: 105801 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1285122 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0228. Min Act: -0.0003

Data Index: 205024 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1258741 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0204. Min Act: -0.0003

Data Index: 360110 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0225. Min Act: -0.0002

Data Index: 323139 (C4 (Web Text))

Max Activating Token Index: 222