Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 95 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0371. Min Act: -0.0003

Data Index: 174692 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0334. Min Act: -0.0003

Data Index: 886738 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0376. Min Act: -0.0003

Data Index: 138394 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0350. Min Act: -0.0003

Data Index: 1217399 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1118441 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0322. Min Act: -0.0003

Data Index: 523652 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0296. Min Act: -0.0004

Data Index: 596311 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0279. Min Act: -0.0003

Data Index: 863679 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1111403 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0322. Min Act: -0.0003

Data Index: 992792 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1100821 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0318. Min Act: -0.0003

Data Index: 379378 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1318113 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0314. Min Act: -0.0003

Data Index: 748923 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0316. Min Act: -0.0003

Data Index: 208272 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0292. Min Act: -0.0003

Data Index: 581394 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1200860 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0308. Min Act: -0.0003

Data Index: 3370 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0296. Min Act: -0.0003

Data Index: 947008 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0302. Min Act: -0.0004

Data Index: 897673 (C4 (Web Text))

Max Activating Token Index: 996