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

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

Neuron 3728 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: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0003

Data Index: 664447 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1153889 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0321. Min Act: -0.0002

Data Index: 557578 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0299. Min Act: -0.0002

Data Index: 954675 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0311. Min Act: -0.0002

Data Index: 958049 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0307. Min Act: -0.0002

Data Index: 588980 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1248276 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0287. Min Act: -0.0003

Data Index: 692157 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0282. Min Act: -0.0003

Data Index: 875059 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0280. Min Act: -0.0002

Data Index: 151770 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1121955 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0274. Min Act: -0.0003

Data Index: 932341 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1020363 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1329214 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0274. Min Act: -0.0003

Data Index: 708091 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1160242 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0269. Min Act: -0.0002

Data Index: 889611 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0266. Min Act: -0.0002

Data Index: 903869 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1273425 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0252. Min Act: -0.0002

Data Index: 216301 (C4 (Web Text))

Max Activating Token Index: 10