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

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

Neuron 402 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1221058 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1288847 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0339. Min Act: -0.0002

Data Index: 948356 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1301721 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0412. Min Act: -0.0002

Data Index: 658218 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0372. Min Act: -0.0002

Data Index: 487273 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0365. Min Act: -0.0002

Data Index: 383146 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0381. Min Act: -0.0002

Data Index: 306724 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0366. Min Act: -0.0002

Data Index: 694631 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0346. Min Act: -0.0002

Data Index: 281378 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1330372 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0308. Min Act: -0.0002

Data Index: 66270 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0355. Min Act: -0.0001

Data Index: 658541 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0351. Min Act: -0.0001

Data Index: 461255 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0381. Min Act: -0.0002

Data Index: 478687 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0324. Min Act: -0.0002

Data Index: 129732 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0381. Min Act: -0.0002

Data Index: 569567 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1410613 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0352. Min Act: -0.0002

Data Index: 903183 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0348. Min Act: -0.0002

Data Index: 567990 (C4 (Web Text))

Max Activating Token Index: 409