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

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

Neuron 263 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: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0002

Data Index: 640526 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0292. Min Act: -0.0003

Data Index: 359412 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0294. Min Act: -0.0003

Data Index: 379552 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0274. Min Act: -0.0003

Data Index: 520490 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0277. Min Act: -0.0002

Data Index: 528685 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0273. Min Act: -0.0003

Data Index: 591132 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0255. Min Act: -0.0003

Data Index: 575211 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1029779 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0267. Min Act: -0.0002

Data Index: 505734 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1265626 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0254. Min Act: -0.0002

Data Index: 560340 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0289. Min Act: -0.0003

Data Index: 367836 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0264. Min Act: -0.0003

Data Index: 400900 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0250. Min Act: -0.0002

Data Index: 455818 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0252. Min Act: -0.0003

Data Index: 16473 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0236. Min Act: -0.0002

Data Index: 550038 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1210507 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0249. Min Act: -0.0003

Data Index: 604169 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0247. Min Act: -0.0002

Data Index: 989943 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0235. Min Act: -0.0003

Data Index: 811660 (C4 (Web Text))

Max Activating Token Index: 688