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

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

Neuron 1330 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: 0.4269. Min Range: -0.4269

Max Act: 0.4269. Min Act: -0.0000

Data Index: 303758 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3328. Min Act: -0.0000

Data Index: 442492 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3059. Min Act: -0.0000

Data Index: 578810 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2791. Min Act: -0.0000

Data Index: 251569 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2829. Min Act: -0.0000

Data Index: 241779 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1648734 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2859. Min Act: -0.0000

Data Index: 851880 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2772. Min Act: -0.0000

Data Index: 240736 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1057378 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1173256 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1654110 (Python Code)

Max Activating Token Index: 1019

Text #11

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2645. Min Act: -0.0000

Data Index: 707386 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1614217 (Python Code)

Max Activating Token Index: 829

Text #13

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1429413 (Python Code)

Max Activating Token Index: 706

Text #14

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2556. Min Act: -0.0000

Data Index: 810241 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1464676 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2510. Min Act: -0.0000

Data Index: 513956 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2517. Min Act: -0.0000

Data Index: 108402 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1329236 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.2320. Min Act: -0.0000

Data Index: 425450 (C4 (Web Text))

Max Activating Token Index: 234