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

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

Neuron 3445 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: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1266177 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1316338 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0309. Min Act: -0.0002

Data Index: 677542 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0271. Min Act: -0.0002

Data Index: 605427 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0262. Min Act: -0.0002

Data Index: 767633 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1025902 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0294. Min Act: -0.0002

Data Index: 58048 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0228. Min Act: -0.0002

Data Index: 315263 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0249. Min Act: -0.0002

Data Index: 285004 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1298940 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0257. Min Act: -0.0002

Data Index: 167287 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0293. Min Act: -0.0002

Data Index: 829333 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0214. Min Act: -0.0002

Data Index: 996875 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0230. Min Act: -0.0002

Data Index: 438487 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1018712 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0224. Min Act: -0.0002

Data Index: 661770 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1114403 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0274. Min Act: -0.0002

Data Index: 868172 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0220. Min Act: -0.0002

Data Index: 946943 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0236. Min Act: -0.0002

Data Index: 811286 (C4 (Web Text))

Max Activating Token Index: 707