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

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

Neuron 2915 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.5960. Min Act: -0.0000

Data Index: 166810 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2314. Min Act: -0.0000

Data Index: 669791 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1155802 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0386. Min Act: -0.0000

Data Index: 487528 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0749. Min Act: -0.0000

Data Index: 752697 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0083. Min Act: -0.0000

Data Index: 668317 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0051. Min Act: -0.0000

Data Index: 328650 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0628. Min Act: -0.0000

Data Index: 882734 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1188249 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0405. Min Act: -0.0000

Data Index: 173155 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1035797 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1162282 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0038. Min Act: -0.0000

Data Index: 744767 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9902. Min Act: -0.0000

Data Index: 609948 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9889. Min Act: -0.0000

Data Index: 439571 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0376. Min Act: -0.0000

Data Index: 106250 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1225059 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1067427 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8998. Min Act: -0.0000

Data Index: 213999 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1047693 (C4 (Web Text))

Max Activating Token Index: 86