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

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

Neuron 810 in Layer 1

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: 742941 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1525036 (Python Code)

Max Activating Token Index: 403

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1217401 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1562024 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1443299 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0273. Min Act: -0.0003

Data Index: 934234 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0263. Min Act: -0.0002

Data Index: 537522 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1519672 (Python Code)

Max Activating Token Index: 390

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0260. Min Act: -0.0003

Data Index: 282664 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1614380 (Python Code)

Max Activating Token Index: 803

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1049921 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0251. Min Act: -0.0002

Data Index: 255865 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1481301 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1241204 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0249. Min Act: -0.0002

Data Index: 918786 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1417184 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1556774 (Python Code)

Max Activating Token Index: 369

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1447778 (Python Code)

Max Activating Token Index: 306

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1410256 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1617046 (Python Code)

Max Activating Token Index: 62