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

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

Neuron 417 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: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0002

Data Index: 502256 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0401. Min Act: -0.0003

Data Index: 148334 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0381. Min Act: -0.0002

Data Index: 301240 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0377. Min Act: -0.0002

Data Index: 969431 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0386. Min Act: -0.0003

Data Index: 767669 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0392. Min Act: -0.0003

Data Index: 243526 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0391. Min Act: -0.0003

Data Index: 139925 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0383. Min Act: -0.0003

Data Index: 642555 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0372. Min Act: -0.0004

Data Index: 15076 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0374. Min Act: -0.0003

Data Index: 201292 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0354. Min Act: -0.0002

Data Index: 396144 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0365. Min Act: -0.0002

Data Index: 164776 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1044744 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0352. Min Act: -0.0002

Data Index: 323446 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0316. Min Act: -0.0002

Data Index: 890341 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0356. Min Act: -0.0003

Data Index: 440982 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1088283 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0349. Min Act: -0.0002

Data Index: 439852 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0348. Min Act: -0.0002

Data Index: 450969 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0352. Min Act: -0.0004

Data Index: 688697 (C4 (Web Text))

Max Activating Token Index: 463