Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 753 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0005

Data Index: 543374 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0234. Min Act: -0.0005

Data Index: 1268964 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0224. Min Act: -0.0005

Data Index: 1194669 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0222. Min Act: -0.0005

Data Index: 828617 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0221. Min Act: -0.0005

Data Index: 868156 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0216. Min Act: -0.0005

Data Index: 734499 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0220. Min Act: -0.0005

Data Index: 1275639 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0218. Min Act: -0.0005

Data Index: 382083 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0216. Min Act: -0.0005

Data Index: 357660 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0206. Min Act: -0.0005

Data Index: 215625 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0211. Min Act: -0.0006

Data Index: 511468 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1259284 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1295027 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1079696 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0201. Min Act: -0.0005

Data Index: 861413 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0200. Min Act: -0.0005

Data Index: 497250 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0199. Min Act: -0.0005

Data Index: 743048 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0005

Data Index: 844935 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0196. Min Act: -0.0005

Data Index: 221658 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0201. Min Act: -0.0005

Data Index: 223495 (C4 (Web Text))

Max Activating Token Index: 105