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

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

Neuron 494 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0006

Data Index: 894086 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1120998 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0225. Min Act: -0.0005

Data Index: 877114 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0222. Min Act: -0.0005

Data Index: 1141582 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0221. Min Act: -0.0005

Data Index: 783214 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0215. Min Act: -0.0006

Data Index: 495178 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0218. Min Act: -0.0006

Data Index: 209424 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0217. Min Act: -0.0006

Data Index: 130451 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0217. Min Act: -0.0005

Data Index: 30625 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0216. Min Act: -0.0006

Data Index: 865977 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0219. Min Act: -0.0006

Data Index: 863103 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0215. Min Act: -0.0006

Data Index: 754243 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0215. Min Act: -0.0005

Data Index: 669371 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0214. Min Act: -0.0005

Data Index: 1287054 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0214. Min Act: -0.0006

Data Index: 274457 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0210. Min Act: -0.0006

Data Index: 806478 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0213. Min Act: -0.0005

Data Index: 1655336 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0212. Min Act: -0.0006

Data Index: 674666 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0212. Min Act: -0.0006

Data Index: 230369 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0212. Min Act: -0.0006

Data Index: 810045 (C4 (Web Text))

Max Activating Token Index: 1016