Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1605 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1269535 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0497. Min Act: -0.0001

Data Index: 149674 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0476. Min Act: -0.0001

Data Index: 811025 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1180680 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0463. Min Act: -0.0001

Data Index: 863825 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1507781 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0430. Min Act: -0.0001

Data Index: 277729 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0476. Min Act: -0.0001

Data Index: 134213 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0426. Min Act: -0.0001

Data Index: 115181 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1300868 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0396. Min Act: -0.0001

Data Index: 184325 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0385. Min Act: -0.0001

Data Index: 500632 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0421. Min Act: -0.0001

Data Index: 768474 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1563428 (Python Code)

Max Activating Token Index: 288

Text #14

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1077281 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1081751 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1028990 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1609278 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0426. Min Act: -0.0001

Data Index: 932242 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0402. Min Act: -0.0001

Data Index: 342272 (C4 (Web Text))

Max Activating Token Index: 285