Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4713 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0828. Min Act: -0.0000

Data Index: 636638 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0696. Min Act: -0.0000

Data Index: 848720 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1213676 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9446. Min Act: -0.0000

Data Index: 25463 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9065. Min Act: -0.0000

Data Index: 50783 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9035. Min Act: -0.0000

Data Index: 727623 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1308161 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.7875. Min Act: -0.0000

Data Index: 187794 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8948. Min Act: -0.0000

Data Index: 510376 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8082. Min Act: -0.0000

Data Index: 15271 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8007. Min Act: -0.0000

Data Index: 84552 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.7983. Min Act: -0.0000

Data Index: 446752 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8386. Min Act: -0.0000

Data Index: 430164 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.7627. Min Act: -0.0000

Data Index: 265416 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8097. Min Act: -0.0000

Data Index: 469078 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.7733. Min Act: -0.0000

Data Index: 426228 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.7183. Min Act: -0.0000

Data Index: 920647 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.7754. Min Act: -0.0000

Data Index: 680628 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.7179. Min Act: -0.0000

Data Index: 124595 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.7957. Min Act: -0.0000

Data Index: 978841 (C4 (Web Text))

Max Activating Token Index: 708