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

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

Neuron 196 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.8308. Min Act: -0.0002

Data Index: 697020 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7966. Min Act: -0.0002

Data Index: 483839 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7813. Min Act: -0.0003

Data Index: 838437 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.8098. Min Act: -0.0002

Data Index: 46274 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.8017. Min Act: -0.0002

Data Index: 1278835 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7928. Min Act: -0.0002

Data Index: 844020 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7653. Min Act: -0.0002

Data Index: 48914 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7661. Min Act: -0.0002

Data Index: 139445 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7536. Min Act: -0.0002

Data Index: 228506 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7499. Min Act: -0.0002

Data Index: 647278 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7578. Min Act: -0.0002

Data Index: 627800 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7420. Min Act: -0.0002

Data Index: 679469 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7453. Min Act: -0.0002

Data Index: 1265817 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7424. Min Act: -0.0002

Data Index: 309934 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7378. Min Act: -0.0002

Data Index: 1074732 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7384. Min Act: -0.0003

Data Index: 426555 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7446. Min Act: -0.0002

Data Index: 1058880 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7473. Min Act: -0.0002

Data Index: 96975 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7324. Min Act: -0.0002

Data Index: 328564 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7140. Min Act: -0.0002

Data Index: 457321 (C4 (Web Text))

Max Activating Token Index: 186