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

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

Neuron 307 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.7427. Min Act: -0.0002

Data Index: 1042547 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6881. Min Act: -0.0002

Data Index: 1124180 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5519. Min Act: -0.0002

Data Index: 796864 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5779. Min Act: -0.0002

Data Index: 1220558 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5486. Min Act: -0.0002

Data Index: 520290 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5431. Min Act: -0.0002

Data Index: 583203 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5167. Min Act: -0.0002

Data Index: 3731 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5305. Min Act: -0.0002

Data Index: 39578 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5116. Min Act: -0.0002

Data Index: 749909 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5017. Min Act: -0.0002

Data Index: 1301226 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.4315. Min Act: -0.0002

Data Index: 409761 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.4386. Min Act: -0.0002

Data Index: 1026037 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.4570. Min Act: -0.0002

Data Index: 865891 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.4080. Min Act: -0.0002

Data Index: 392637 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.4149. Min Act: -0.0002

Data Index: 949374 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.4014. Min Act: -0.0002

Data Index: 355541 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.3404. Min Act: -0.0002

Data Index: 479896 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.3572. Min Act: -0.0002

Data Index: 1417995 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.3798. Min Act: -0.0002

Data Index: 29616 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.3102. Min Act: -0.0002

Data Index: 518557 (C4 (Web Text))

Max Activating Token Index: 658