Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3500 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0002

Data Index: 18752 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0415. Min Act: -0.0002

Data Index: 85606 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1090215 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0383. Min Act: -0.0002

Data Index: 479884 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0381. Min Act: -0.0003

Data Index: 813891 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0361. Min Act: -0.0002

Data Index: 61396 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0367. Min Act: -0.0002

Data Index: 335219 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1336532 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1196570 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0371. Min Act: -0.0002

Data Index: 349741 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0348. Min Act: -0.0003

Data Index: 320274 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0346. Min Act: -0.0002

Data Index: 861506 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0339. Min Act: -0.0002

Data Index: 230024 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0350. Min Act: -0.0002

Data Index: 919549 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0355. Min Act: -0.0002

Data Index: 582157 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0337. Min Act: -0.0002

Data Index: 431766 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1091867 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1144128 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0327. Min Act: -0.0002

Data Index: 10236 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0308. Min Act: -0.0002

Data Index: 190503 (C4 (Web Text))

Max Activating Token Index: 176