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

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

Neuron 5120 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: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0002

Data Index: 783170 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0394. Min Act: -0.0002

Data Index: 322768 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0396. Min Act: -0.0002

Data Index: 674045 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1067862 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1234134 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0363. Min Act: -0.0002

Data Index: 322699 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0322. Min Act: -0.0002

Data Index: 667039 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1319775 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0330. Min Act: -0.0002

Data Index: 175681 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0319. Min Act: -0.0002

Data Index: 376756 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0314. Min Act: -0.0002

Data Index: 733958 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0317. Min Act: -0.0002

Data Index: 691266 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0321. Min Act: -0.0002

Data Index: 454322 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0309. Min Act: -0.0002

Data Index: 524615 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1335547 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0301. Min Act: -0.0002

Data Index: 315347 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0315. Min Act: -0.0002

Data Index: 312420 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1304836 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1137833 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1310391 (C4 (Web Text))

Max Activating Token Index: 320