Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1821 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0362. Min Act: -0.0006

Data Index: 825275 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0376. Min Act: -0.0006

Data Index: 747108 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0341. Min Act: -0.0006

Data Index: 158874 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0339. Min Act: -0.0006

Data Index: 795316 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0323. Min Act: -0.0006

Data Index: 230223 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0313. Min Act: -0.0006

Data Index: 100676 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0321. Min Act: -0.0006

Data Index: 199659 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1244758 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0326. Min Act: -0.0006

Data Index: 970493 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0314. Min Act: -0.0006

Data Index: 855047 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0322. Min Act: -0.0006

Data Index: 117695 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0320. Min Act: -0.0006

Data Index: 133758 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0305. Min Act: -0.0006

Data Index: 881496 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0337. Min Act: -0.0006

Data Index: 396647 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0313. Min Act: -0.0006

Data Index: 630180 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1320238 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0322. Min Act: -0.0006

Data Index: 948528 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1170936 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0294. Min Act: -0.0006

Data Index: 55015 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0294. Min Act: -0.0006

Data Index: 326846 (C4 (Web Text))

Max Activating Token Index: 167