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

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

Neuron 4773 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: 0.0394. Min Range: -0.0394

Max Act: 0.0391. Min Act: -0.0002

Data Index: 194013 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0002

Data Index: 820482 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1145263 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1117730 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0290. Min Act: -0.0002

Data Index: 709615 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1316043 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0273. Min Act: -0.0002

Data Index: 391232 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0279. Min Act: -0.0002

Data Index: 334792 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0284. Min Act: -0.0002

Data Index: 204396 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0282. Min Act: -0.0002

Data Index: 163295 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0274. Min Act: -0.0003

Data Index: 904189 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1328943 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0246. Min Act: -0.0002

Data Index: 191565 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0242. Min Act: -0.0002

Data Index: 189163 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0265. Min Act: -0.0002

Data Index: 95393 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0280. Min Act: -0.0002

Data Index: 544602 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1124830 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0243. Min Act: -0.0002

Data Index: 575630 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0251. Min Act: -0.0002

Data Index: 509455 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0278. Min Act: -0.0002

Data Index: 841970 (C4 (Web Text))

Max Activating Token Index: 203