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

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

Neuron 1013 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: 0.3567. Min Range: -0.3567

Max Act: 0.3567. Min Act: -0.0000

Data Index: 830354 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3365. Min Act: -0.0000

Data Index: 439724 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3311. Min Act: -0.0000

Data Index: 197124 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3164. Min Act: -0.0001

Data Index: 94182 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3125. Min Act: -0.0000

Data Index: 606406 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3032. Min Act: -0.0001

Data Index: 854956 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3129. Min Act: -0.0000

Data Index: 222512 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1232660 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1329837 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1328475 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2966. Min Act: -0.0000

Data Index: 604841 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2718. Min Act: -0.0001

Data Index: 884900 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1265578 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2811. Min Act: -0.0000

Data Index: 520922 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2692. Min Act: -0.0000

Data Index: 214464 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2797. Min Act: -0.0000

Data Index: 547050 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2892. Min Act: -0.0000

Data Index: 593896 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2774. Min Act: -0.0001

Data Index: 614996 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2870. Min Act: -0.0000

Data Index: 166024 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2777. Min Act: -0.0000

Data Index: 588783 (C4 (Web Text))

Max Activating Token Index: 340