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

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

Neuron 1684 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: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0003

Data Index: 786164 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1281662 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0246. Min Act: -0.0003

Data Index: 506051 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0230. Min Act: -0.0003

Data Index: 798652 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0228. Min Act: -0.0003

Data Index: 846996 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0230. Min Act: -0.0003

Data Index: 412204 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0228. Min Act: -0.0003

Data Index: 630230 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1512893 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0220. Min Act: -0.0003

Data Index: 947260 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0225. Min Act: -0.0003

Data Index: 911523 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0218. Min Act: -0.0003

Data Index: 48065 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0220. Min Act: -0.0003

Data Index: 392775 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0220. Min Act: -0.0003

Data Index: 251198 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0219. Min Act: -0.0003

Data Index: 699750 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0221. Min Act: -0.0003

Data Index: 847292 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0213. Min Act: -0.0003

Data Index: 71658 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0208. Min Act: -0.0003

Data Index: 596849 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0210. Min Act: -0.0003

Data Index: 508820 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0207. Min Act: -0.0003

Data Index: 471369 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1237889 (C4 (Web Text))

Max Activating Token Index: 822