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

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

Neuron 4427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0226. Min Act: -0.0002

Data Index: 467981 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0230. Min Act: -0.0002

Data Index: 795632 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0215. Min Act: -0.0002

Data Index: 492380 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0241. Min Act: -0.0002

Data Index: 94196 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0213. Min Act: -0.0002

Data Index: 619713 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0192. Min Act: -0.0002

Data Index: 614363 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0188. Min Act: -0.0002

Data Index: 167829 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0195. Min Act: -0.0002

Data Index: 593216 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0208. Min Act: -0.0002

Data Index: 248302 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0182. Min Act: -0.0002

Data Index: 533578 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1121741 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0200. Min Act: -0.0002

Data Index: 355919 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0195. Min Act: -0.0002

Data Index: 269678 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0195. Min Act: -0.0002

Data Index: 216525 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0202. Min Act: -0.0002

Data Index: 12680 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1305281 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0191. Min Act: -0.0002

Data Index: 174529 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0184. Min Act: -0.0002

Data Index: 547425 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0203. Min Act: -0.0002

Data Index: 654483 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1061210 (C4 (Web Text))

Max Activating Token Index: 737