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

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

Neuron 3818 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: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0003

Data Index: 109349 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1517305 (Python Code)

Max Activating Token Index: 516

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0275. Min Act: -0.0003

Data Index: 816658 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1170732 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1380867 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0269. Min Act: -0.0003

Data Index: 496517 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1384148 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1499328 (Python Code)

Max Activating Token Index: 425

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1453820 (Python Code)

Max Activating Token Index: 236

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0249. Min Act: -0.0003

Data Index: 937923 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0251. Min Act: -0.0002

Data Index: 131832 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0259. Min Act: -0.0003

Data Index: 988166 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0256. Min Act: -0.0002

Data Index: 252135 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0249. Min Act: -0.0003

Data Index: 733305 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1060379 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0245. Min Act: -0.0003

Data Index: 976899 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0247. Min Act: -0.0003

Data Index: 422269 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0235. Min Act: -0.0003

Data Index: 192079 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0236. Min Act: -0.0003

Data Index: 632901 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0237. Min Act: -0.0003

Data Index: 847865 (C4 (Web Text))

Max Activating Token Index: 323