Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5679 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0002

Data Index: 555006 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0471. Min Act: -0.0002

Data Index: 310217 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0473. Min Act: -0.0002

Data Index: 176453 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0459. Min Act: -0.0002

Data Index: 122626 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0427. Min Act: -0.0002

Data Index: 246596 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0409. Min Act: -0.0002

Data Index: 711353 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0419. Min Act: -0.0002

Data Index: 234640 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0399. Min Act: -0.0002

Data Index: 875324 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0381. Min Act: -0.0002

Data Index: 402499 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1292125 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1252135 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1090587 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0387. Min Act: -0.0002

Data Index: 198055 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1315985 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0381. Min Act: -0.0002

Data Index: 488441 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0366. Min Act: -0.0002

Data Index: 938047 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0351. Min Act: -0.0002

Data Index: 5818 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0345. Min Act: -0.0002

Data Index: 722749 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0365. Min Act: -0.0002

Data Index: 447698 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0357. Min Act: -0.0002

Data Index: 511459 (C4 (Web Text))

Max Activating Token Index: 156