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

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

Neuron 782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.8020. Min Act: -0.0000

Data Index: 563356 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3875. Min Act: -0.0000

Data Index: 353665 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3203. Min Act: -0.0000

Data Index: 1323750 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.5395. Min Act: -0.0000

Data Index: 1018022 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.1237. Min Act: -0.0000

Data Index: 787544 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.2895. Min Act: -0.0000

Data Index: 1117621 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.0735. Min Act: -0.0000

Data Index: 996429 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.1782. Min Act: -0.0000

Data Index: 1332853 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.2486. Min Act: -0.0000

Data Index: 1232822 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.6840. Min Act: -0.0000

Data Index: 1158015 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.8185. Min Act: -0.0000

Data Index: 1193264 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.7984. Min Act: -0.0000

Data Index: 792586 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.8071. Min Act: -0.0000

Data Index: 141842 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.7544. Min Act: -0.0000

Data Index: 168960 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.7071. Min Act: -0.0000

Data Index: 301303 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.4344. Min Act: -0.0000

Data Index: 77215 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.4730. Min Act: -0.0000

Data Index: 667052 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.3887. Min Act: -0.0000

Data Index: 1046718 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.5574. Min Act: -0.0000

Data Index: 615645 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 5.8020. Min Range: -5.8020

Max Act: 4.5593. Min Act: -0.0000

Data Index: 1046899 (C4 (Web Text))

Max Activating Token Index: 128