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

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

Neuron 2962 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.4098. Min Act: -0.0000

Data Index: 348974 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1632643 (Python Code)

Max Activating Token Index: 719

Text #2

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3576. Min Act: -0.0000

Data Index: 957450 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3190. Min Act: -0.0001

Data Index: 1541665 (Python Code)

Max Activating Token Index: 813

Text #4

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2980. Min Act: -0.0001

Data Index: 609711 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2959. Min Act: -0.0001

Data Index: 1311773 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3096. Min Act: -0.0000

Data Index: 166754 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3000. Min Act: -0.0001

Data Index: 567917 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2894. Min Act: -0.0000

Data Index: 940842 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2879. Min Act: -0.0001

Data Index: 779311 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3062. Min Act: -0.0000

Data Index: 669693 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2912. Min Act: -0.0001

Data Index: 1543342 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1099010 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1281754 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2740. Min Act: -0.0000

Data Index: 994741 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2458. Min Act: -0.0000

Data Index: 554693 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1486008 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2895. Min Act: -0.0001

Data Index: 1610869 (Python Code)

Max Activating Token Index: 930

Text #18

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2787. Min Act: -0.0001

Data Index: 1522664 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2782. Min Act: -0.0001

Data Index: 1384360 (Python Code)

Max Activating Token Index: 248