Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 45 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0472. Min Act: -0.0003

Data Index: 627874 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0502. Min Act: -0.0003

Data Index: 305906 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1090775 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0426. Min Act: -0.0003

Data Index: 736768 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0436. Min Act: -0.0003

Data Index: 603057 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1010925 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0407. Min Act: -0.0002

Data Index: 155959 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1008050 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0378. Min Act: -0.0003

Data Index: 601292 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0366. Min Act: -0.0004

Data Index: 447156 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1274604 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1309530 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0356. Min Act: -0.0003

Data Index: 521692 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1141193 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0317. Min Act: -0.0003

Data Index: 396763 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0317. Min Act: -0.0004

Data Index: 36814 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0322. Min Act: -0.0003

Data Index: 471149 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0310. Min Act: -0.0002

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1301219 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0322. Min Act: -0.0003

Data Index: 445616 (C4 (Web Text))

Max Activating Token Index: 100