Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1920 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1257. Min Act: -0.0000

Data Index: 884671 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1017. Min Act: -0.0001

Data Index: 727662 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0995. Min Act: -0.0000

Data Index: 990882 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1250421 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0889. Min Act: -0.0000

Data Index: 42147 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1267308 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0803. Min Act: -0.0001

Data Index: 55831 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0854. Min Act: -0.0000

Data Index: 198097 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1352186 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0879. Min Act: -0.0000

Data Index: 790635 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0812. Min Act: -0.0000

Data Index: 30855 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0887. Min Act: -0.0000

Data Index: 913952 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1032690 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0813. Min Act: -0.0000

Data Index: 563829 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0751. Min Act: -0.0001

Data Index: 274456 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0798. Min Act: -0.0000

Data Index: 629858 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0733. Min Act: -0.0000

Data Index: 500493 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0758. Min Act: -0.0000

Data Index: 194033 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1137682 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0750. Min Act: -0.0001

Data Index: 453033 (C4 (Web Text))

Max Activating Token Index: 392