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

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

Neuron 1460 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0006

Data Index: 217364 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1203962 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1047059 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1221134 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0249. Min Act: -0.0006

Data Index: 714149 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0248. Min Act: -0.0006

Data Index: 827331 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0245. Min Act: -0.0006

Data Index: 197975 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1105684 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0249. Min Act: -0.0006

Data Index: 944183 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0242. Min Act: -0.0006

Data Index: 572362 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0242. Min Act: -0.0006

Data Index: 889232 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0235. Min Act: -0.0006

Data Index: 429490 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1203148 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0237. Min Act: -0.0006

Data Index: 440584 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0239. Min Act: -0.0006

Data Index: 724826 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1222061 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0237. Min Act: -0.0006

Data Index: 734434 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0237. Min Act: -0.0006

Data Index: 107882 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0236. Min Act: -0.0006

Data Index: 401880 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0235. Min Act: -0.0006

Data Index: 88290 (C4 (Web Text))

Max Activating Token Index: 576