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

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

Neuron 1028 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: 0.9274. Min Range: -0.9274

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1272089 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8348. Min Act: -0.0000

Data Index: 926563 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7991. Min Act: -0.0000

Data Index: 92481 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7884. Min Act: -0.0001

Data Index: 950971 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7207. Min Act: -0.0000

Data Index: 958950 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7212. Min Act: -0.0001

Data Index: 854832 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6716. Min Act: -0.0000

Data Index: 946233 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6808. Min Act: -0.0001

Data Index: 685849 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6662. Min Act: -0.0001

Data Index: 17866 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6605. Min Act: -0.0000

Data Index: 566365 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1342439 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6591. Min Act: -0.0001

Data Index: 1017175 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6687. Min Act: -0.0001

Data Index: 1059155 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1130370 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6396. Min Act: -0.0001

Data Index: 531604 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6301. Min Act: -0.0000

Data Index: 465013 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6495. Min Act: -0.0000

Data Index: 7743 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6055. Min Act: -0.0000

Data Index: 487434 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.5948. Min Act: -0.0001

Data Index: 711168 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6369. Min Act: -0.0001

Data Index: 112212 (C4 (Web Text))

Max Activating Token Index: 639