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

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

Neuron 1986 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1359587 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0342. Min Act: -0.0001

Data Index: 945363 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0304. Min Act: -0.0001

Data Index: 840066 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1010995 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0306. Min Act: -0.0001

Data Index: 603154 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0267. Min Act: -0.0001

Data Index: 439346 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0309. Min Act: -0.0001

Data Index: 514572 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1563053 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0264. Min Act: -0.0001

Data Index: 475893 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0295. Min Act: -0.0001

Data Index: 425398 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0297. Min Act: -0.0001

Data Index: 683613 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1073868 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1174337 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0254. Min Act: -0.0001

Data Index: 908829 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1552555 (Python Code)

Max Activating Token Index: 564

Text #15

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0272. Min Act: -0.0001

Data Index: 80558 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1592385 (Python Code)

Max Activating Token Index: 618

Text #17

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1510131 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1530076 (Python Code)

Max Activating Token Index: 824

Text #19

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0267. Min Act: -0.0001

Data Index: 445300 (C4 (Web Text))

Max Activating Token Index: 561