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

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

Neuron 1652 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.5828. Min Act: -0.0001

Data Index: 626206 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.5278. Min Act: -0.0000

Data Index: 56779 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.4054. Min Act: -0.0001

Data Index: 931436 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.2208. Min Act: -0.0000

Data Index: 519006 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.2437. Min Act: -0.0000

Data Index: 970163 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1562. Min Act: -0.0000

Data Index: 962499 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1786. Min Act: -0.0001

Data Index: 1247281 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1978. Min Act: -0.0000

Data Index: 985621 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.0946. Min Act: -0.0000

Data Index: 571879 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.0561. Min Act: -0.0000

Data Index: 178500 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1093. Min Act: -0.0001

Data Index: 207229 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.0429. Min Act: -0.0001

Data Index: 1227072 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.0636. Min Act: -0.0001

Data Index: 990578 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1012. Min Act: -0.0001

Data Index: 357653 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1237. Min Act: -0.0000

Data Index: 794554 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.0562. Min Act: -0.0001

Data Index: 263703 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1208. Min Act: -0.0001

Data Index: 1092330 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1142. Min Act: -0.0001

Data Index: 479586 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 1.5828. Min Range: -1.5828

Max Act: 1.1009. Min Act: -0.0001

Data Index: 1192806 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.5828. Min Range: -1.5828

Max Act: 0.9717. Min Act: -0.0001

Data Index: 744751 (C4 (Web Text))

Max Activating Token Index: 655