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

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

Neuron 4744 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1326477 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1058025 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1000782 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.4439. Min Act: -0.0000

Data Index: 804525 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.5565. Min Act: -0.0000

Data Index: 752780 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.4517. Min Act: -0.0000

Data Index: 329743 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.3464. Min Act: -0.0000

Data Index: 988381 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.2627. Min Act: -0.0000

Data Index: 236308 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1345275 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0817. Min Act: -0.0000

Data Index: 635808 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0749. Min Act: -0.0000

Data Index: 283810 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1254068 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1223703 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1004008 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0035. Min Act: -0.0000

Data Index: 945146 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1402827 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 1.6662. Min Range: -1.6662

Max Act: 0.9855. Min Act: -0.0000

Data Index: 454365 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0357. Min Act: -0.0000

Data Index: 518056 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0720. Min Act: -0.0000

Data Index: 97445 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0158. Min Act: -0.0000

Data Index: 405627 (C4 (Web Text))

Max Activating Token Index: 283