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

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

Neuron 1680 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.3057. Min Act: -0.0001

Data Index: 645772 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2703. Min Act: -0.0001

Data Index: 95914 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2563. Min Act: -0.0001

Data Index: 1057511 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.3720. Min Act: -0.0001

Data Index: 873882 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2105. Min Act: -0.0001

Data Index: 556891 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1882. Min Act: -0.0001

Data Index: 460795 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1477. Min Act: -0.0001

Data Index: 512976 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1390. Min Act: -0.0001

Data Index: 1059798 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1664. Min Act: -0.0001

Data Index: 1225243 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1515. Min Act: -0.0001

Data Index: 86925 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2153. Min Act: -0.0001

Data Index: 256445 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0323. Min Act: -0.0001

Data Index: 400367 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1572. Min Act: -0.0001

Data Index: 452079 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0251. Min Act: -0.0001

Data Index: 1116351 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0873. Min Act: -0.0001

Data Index: 1141519 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1179. Min Act: -0.0001

Data Index: 525956 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0582. Min Act: -0.0001

Data Index: 657895 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0905. Min Act: -0.0001

Data Index: 416551 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0514. Min Act: -0.0001

Data Index: 10659 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1034. Min Act: -0.0001

Data Index: 955997 (C4 (Web Text))

Max Activating Token Index: 926