Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 102 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.3242. Min Act: -0.0000

Data Index: 597791 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.2688. Min Act: -0.0000

Data Index: 113773 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.9681. Min Act: -0.0000

Data Index: 1192412 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.8421. Min Act: -0.0000

Data Index: 91979 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.9275. Min Act: -0.0001

Data Index: 999353 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.9871. Min Act: -0.0000

Data Index: 371304 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.7379. Min Act: -0.0000

Data Index: 981978 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1109066 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.9996. Min Act: -0.0000

Data Index: 1075866 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.6914. Min Act: -0.0000

Data Index: 1025624 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.6705. Min Act: -0.0000

Data Index: 827554 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.6072. Min Act: -0.0000

Data Index: 1315951 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1057483 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.5771. Min Act: -0.0000

Data Index: 390985 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1124399 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.5419. Min Act: -0.0001

Data Index: 680637 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.6117. Min Act: -0.0000

Data Index: 221248 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.6054. Min Act: -0.0001

Data Index: 861803 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.5966. Min Act: -0.0001

Data Index: 211393 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1284796 (C4 (Web Text))

Max Activating Token Index: 969