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

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

Neuron 4797 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.7068. Min Act: -0.0000

Data Index: 589958 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.7195. Min Act: -0.0000

Data Index: 393430 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.5224. Min Act: -0.0000

Data Index: 277568 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.5396. Min Act: -0.0000

Data Index: 16277 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.3450. Min Act: -0.0000

Data Index: 871813 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.3257. Min Act: -0.0000

Data Index: 291084 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.3042. Min Act: -0.0001

Data Index: 196046 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.2597. Min Act: -0.0000

Data Index: 325410 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.2612. Min Act: -0.0000

Data Index: 1298879 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1284498 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.1834. Min Act: -0.0000

Data Index: 610496 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.1785. Min Act: -0.0000

Data Index: 602450 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.2385. Min Act: -0.0000

Data Index: 24742 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1100823 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1261302 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.2798. Min Act: -0.0000

Data Index: 218430 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.1412. Min Act: -0.0000

Data Index: 52465 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.2084. Min Act: -0.0000

Data Index: 1120491 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.1397. Min Act: -0.0001

Data Index: 578566 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.7195. Min Range: -1.7195

Max Act: 1.1992. Min Act: -0.0000

Data Index: 737443 (C4 (Web Text))

Max Activating Token Index: 695