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

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

Neuron 2695 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1499036 (Python Code)

Max Activating Token Index: 626

Text #1

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2499. Min Act: 0.0001

Data Index: 1466944 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2425. Min Act: -0.0000

Data Index: 969028 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2408. Min Act: 0.0000

Data Index: 933789 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2362. Min Act: -0.0000

Data Index: 876189 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2176. Min Act: 0.0001

Data Index: 1635342 (Python Code)

Max Activating Token Index: 345

Text #6

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2196. Min Act: -0.0000

Data Index: 17595 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1971. Min Act: 0.0000

Data Index: 1490762 (Python Code)

Max Activating Token Index: 855

Text #8

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2005. Min Act: 0.0002

Data Index: 1437125 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1857. Min Act: -0.0000

Data Index: 900621 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1883. Min Act: 0.0001

Data Index: 1628007 (Python Code)

Max Activating Token Index: 422

Text #11

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1316293 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1166424 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1315808 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1144833 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1791. Min Act: 0.0000

Data Index: 1305510 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1759. Min Act: 0.0000

Data Index: 614992 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1725. Min Act: -0.0000

Data Index: 416781 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1776. Min Act: 0.0000

Data Index: 1491510 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1136892 (C4 (Web Text))

Max Activating Token Index: 458