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

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

Neuron 4226 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1485078 (Python Code)

Max Activating Token Index: 187

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1177671 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1325969 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0306. Min Act: -0.0002

Data Index: 862777 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0303. Min Act: -0.0002

Data Index: 410952 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0300. Min Act: -0.0002

Data Index: 385783 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1196278 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1118132 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0280. Min Act: -0.0002

Data Index: 314495 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1256575 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0282. Min Act: -0.0002

Data Index: 526836 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0288. Min Act: -0.0002

Data Index: 617294 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0281. Min Act: -0.0002

Data Index: 619504 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1274369 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0268. Min Act: -0.0002

Data Index: 699457 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1362827 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0276. Min Act: -0.0002

Data Index: 931662 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0277. Min Act: -0.0002

Data Index: 109850 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0276. Min Act: -0.0002

Data Index: 647799 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1245769 (C4 (Web Text))

Max Activating Token Index: 124