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

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

Neuron 779 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1572772 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1584259 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1418314 (Python Code)

Max Activating Token Index: 496

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1548049 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1455650 (Python Code)

Max Activating Token Index: 902

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1379834 (Python Code)

Max Activating Token Index: 876

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1538688 (Python Code)

Max Activating Token Index: 393

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1387823 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1654911 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1580299 (Python Code)

Max Activating Token Index: 412

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1480100 (Python Code)

Max Activating Token Index: 988

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1552394 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1514387 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1453571 (Python Code)

Max Activating Token Index: 308

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1436336 (Python Code)

Max Activating Token Index: 338

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1541814 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1629608 (Python Code)

Max Activating Token Index: 317

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1608873 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1425738 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1476610 (Python Code)

Max Activating Token Index: 747