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

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

Neuron 3522 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.5814. Min Act: -0.0000

Data Index: 839269 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.3189. Min Act: -0.0000

Data Index: 43742 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.9376. Min Act: -0.0000

Data Index: 533090 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.0634. Min Act: -0.0000

Data Index: 106700 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.9670. Min Act: -0.0000

Data Index: 222871 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.9612. Min Act: -0.0000

Data Index: 1094014 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.0025. Min Act: -0.0000

Data Index: 1122139 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.8055. Min Act: -0.0000

Data Index: 1264970 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.7284. Min Act: -0.0000

Data Index: 1279578 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.5953. Min Act: -0.0000

Data Index: 869082 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.6719. Min Act: -0.0000

Data Index: 1223281 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.7513. Min Act: -0.0000

Data Index: 499220 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.3607. Min Act: -0.0000

Data Index: 108168 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.6242. Min Act: -0.0000

Data Index: 661609 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.3311. Min Act: -0.0000

Data Index: 567684 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.3165. Min Act: -0.0000

Data Index: 266668 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.2433. Min Act: -0.0000

Data Index: 392699 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.1044. Min Act: -0.0000

Data Index: 434600 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.2026. Min Act: -0.0000

Data Index: 124572 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.5814. Min Range: -3.5814

Max Act: 2.0867. Min Act: -0.0000

Data Index: 951773 (C4 (Web Text))

Max Activating Token Index: 78