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

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

Neuron 4759 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.2402. Min Act: -0.0000

Data Index: 208148 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.4714. Min Act: -0.0001

Data Index: 486002 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.2368. Min Act: -0.0001

Data Index: 1014528 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.0741. Min Act: -0.0000

Data Index: 71057 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.0572. Min Act: -0.0000

Data Index: 446630 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.0723. Min Act: -0.0000

Data Index: 55474 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.2869. Min Act: -0.0000

Data Index: 28975 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.1619. Min Act: -0.0000

Data Index: 492255 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.1301. Min Act: -0.0000

Data Index: 621356 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 2.4714. Min Range: -2.4714

Max Act: 1.9813. Min Act: -0.0000

Data Index: 224273 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.0713. Min Act: -0.0000

Data Index: 883948 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 2.4714. Min Range: -2.4714

Max Act: 1.9721. Min Act: -0.0001

Data Index: 1212218 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.0641. Min Act: -0.0000

Data Index: 39327 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 2.4714. Min Range: -2.4714

Max Act: 1.9491. Min Act: -0.0000

Data Index: 756899 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.1498. Min Act: -0.0001

Data Index: 732194 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 2.4714. Min Range: -2.4714

Max Act: 2.0320. Min Act: -0.0000

Data Index: 1169739 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 2.4714. Min Range: -2.4714

Max Act: 1.9683. Min Act: -0.0000

Data Index: 391154 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 2.4714. Min Range: -2.4714

Max Act: 1.8581. Min Act: -0.0000

Data Index: 689767 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 2.4714. Min Range: -2.4714

Max Act: 1.9295. Min Act: -0.0000

Data Index: 363495 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 2.4714. Min Range: -2.4714

Max Act: 1.9331. Min Act: -0.0000

Data Index: 1222573 (C4 (Web Text))

Max Activating Token Index: 948