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

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

Neuron 5586 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: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0002

Data Index: 30749 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0390. Min Act: -0.0002

Data Index: 582572 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0381. Min Act: -0.0002

Data Index: 986613 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0374. Min Act: -0.0002

Data Index: 885335 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0368. Min Act: -0.0002

Data Index: 669380 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0358. Min Act: -0.0002

Data Index: 335719 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1295508 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1150089 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0355. Min Act: -0.0002

Data Index: 860466 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0362. Min Act: -0.0002

Data Index: 776532 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1199719 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1146844 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0346. Min Act: -0.0002

Data Index: 686628 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0349. Min Act: -0.0002

Data Index: 692566 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0343. Min Act: -0.0002

Data Index: 34623 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0346. Min Act: -0.0002

Data Index: 534991 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0359. Min Act: -0.0002

Data Index: 649273 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0347. Min Act: -0.0002

Data Index: 722364 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0339. Min Act: -0.0002

Data Index: 152264 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0316. Min Act: -0.0002

Data Index: 297868 (C4 (Web Text))

Max Activating Token Index: 319