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

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

Neuron 2026 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: 0.3254. Min Range: -0.3254

Max Act: 0.3225. Min Act: -0.0000

Data Index: 761718 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.3254. Min Act: -0.0000

Data Index: 1575096 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.3188. Min Act: -0.0000

Data Index: 99088 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2765. Min Act: -0.0000

Data Index: 328124 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1520059 (Python Code)

Max Activating Token Index: 362

Text #5

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2911. Min Act: -0.0000

Data Index: 523810 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2987. Min Act: -0.0000

Data Index: 395243 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2906. Min Act: -0.0000

Data Index: 872978 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2713. Min Act: -0.0000

Data Index: 483234 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2712. Min Act: -0.0000

Data Index: 41538 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2706. Min Act: -0.0000

Data Index: 212641 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1432393 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2697. Min Act: -0.0000

Data Index: 803944 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2763. Min Act: -0.0000

Data Index: 445595 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1382787 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2646. Min Act: -0.0000

Data Index: 411594 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1592789 (Python Code)

Max Activating Token Index: 778

Text #17

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1504556 (Python Code)

Max Activating Token Index: 848

Text #18

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1502327 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2540. Min Act: -0.0000

Data Index: 95599 (C4 (Web Text))

Max Activating Token Index: 968