Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 727 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0003

Data Index: 314403 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0237. Min Act: -0.0003

Data Index: 219372 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0003

Data Index: 619186 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1194102 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1213725 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1603777 (Python Code)

Max Activating Token Index: 247

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0227. Min Act: -0.0003

Data Index: 462727 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1195843 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1453251 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1443043 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1621258 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1490162 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0175. Min Act: -0.0003

Data Index: 712237 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0194. Min Act: -0.0003

Data Index: 420969 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1294708 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0210. Min Act: -0.0003

Data Index: 918955 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0209. Min Act: -0.0003

Data Index: 80050 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0202. Min Act: -0.0003

Data Index: 556283 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0200. Min Act: -0.0003

Data Index: 326852 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1414208 (Python Code)

Max Activating Token Index: 153