Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5648 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0002

Data Index: 236195 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0401. Min Act: -0.0002

Data Index: 805445 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0389. Min Act: -0.0002

Data Index: 334170 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0370. Min Act: -0.0002

Data Index: 352894 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0348. Min Act: -0.0002

Data Index: 34050 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1145834 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1245400 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0339. Min Act: -0.0002

Data Index: 154782 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1294861 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0334. Min Act: -0.0002

Data Index: 996100 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1017746 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0309. Min Act: -0.0002

Data Index: 291766 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0299. Min Act: -0.0002

Data Index: 189125 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1312350 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1010320 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0297. Min Act: -0.0002

Data Index: 600207 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0293. Min Act: -0.0002

Data Index: 123307 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0290. Min Act: -0.0002

Data Index: 769104 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0279. Min Act: -0.0002

Data Index: 161980 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0288. Min Act: -0.0002

Data Index: 730482 (C4 (Web Text))

Max Activating Token Index: 335