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

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

Neuron 3391 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0003

Data Index: 517499 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0804. Min Act: -0.0003

Data Index: 1342540 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0824. Min Act: -0.0003

Data Index: 179966 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0804. Min Act: -0.0003

Data Index: 500163 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0776. Min Act: -0.0003

Data Index: 808406 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0767. Min Act: -0.0003

Data Index: 683203 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0782. Min Act: -0.0003

Data Index: 222660 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0738. Min Act: -0.0003

Data Index: 436336 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0744. Min Act: -0.0003

Data Index: 250047 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0718. Min Act: -0.0003

Data Index: 59705 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0745. Min Act: -0.0003

Data Index: 259326 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1019608 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0700. Min Act: -0.0003

Data Index: 333292 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0740. Min Act: -0.0003

Data Index: 335956 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0707. Min Act: -0.0003

Data Index: 33851 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0704. Min Act: -0.0003

Data Index: 932506 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0654. Min Act: -0.0003

Data Index: 549990 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0666. Min Act: -0.0003

Data Index: 883501 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0654. Min Act: -0.0003

Data Index: 460974 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1056715 (C4 (Web Text))

Max Activating Token Index: 370