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

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

Neuron 4482 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: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0003

Data Index: 890996 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1245021 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0311. Min Act: -0.0003

Data Index: 958297 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0281. Min Act: -0.0003

Data Index: 541623 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0259. Min Act: -0.0003

Data Index: 121336 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0264. Min Act: -0.0003

Data Index: 545067 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1299067 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0243. Min Act: -0.0003

Data Index: 541588 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1113594 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0231. Min Act: -0.0003

Data Index: 31629 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0228. Min Act: -0.0003

Data Index: 650805 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0225. Min Act: -0.0003

Data Index: 339823 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0226. Min Act: -0.0003

Data Index: 342658 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0226. Min Act: -0.0003

Data Index: 85761 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0211. Min Act: -0.0003

Data Index: 760314 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0223. Min Act: -0.0003

Data Index: 383237 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0217. Min Act: -0.0003

Data Index: 642595 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0215. Min Act: -0.0003

Data Index: 568215 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1195182 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0220. Min Act: -0.0003

Data Index: 695238 (C4 (Web Text))

Max Activating Token Index: 946