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

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

Neuron 838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0300. Min Act: -0.0003

Data Index: 340635 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0294. Min Act: -0.0003

Data Index: 456513 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1354262 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0275. Min Act: -0.0003

Data Index: 724649 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1001495 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0258. Min Act: -0.0003

Data Index: 60099 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0248. Min Act: -0.0003

Data Index: 157815 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0251. Min Act: -0.0003

Data Index: 130008 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0242. Min Act: -0.0003

Data Index: 810547 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0239. Min Act: -0.0003

Data Index: 894150 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0257. Min Act: -0.0003

Data Index: 98433 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1024172 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0220. Min Act: -0.0003

Data Index: 552730 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0227. Min Act: -0.0003

Data Index: 826831 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0233. Min Act: -0.0003

Data Index: 21582 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0227. Min Act: -0.0003

Data Index: 707651 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0227. Min Act: -0.0003

Data Index: 84661 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0221. Min Act: -0.0003

Data Index: 540494 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1435412 (Python Code)

Max Activating Token Index: 642

Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1163860 (C4 (Web Text))

Max Activating Token Index: 872