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

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

Neuron 5640 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: 0.2495. Min Range: -0.2495

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1128729 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2415. Min Act: -0.0000

Data Index: 876913 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2171. Min Act: -0.0001

Data Index: 714930 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2264. Min Act: -0.0001

Data Index: 934400 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1299701 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2114. Min Act: -0.0000

Data Index: 268681 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1862. Min Act: -0.0000

Data Index: 539765 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2089. Min Act: -0.0001

Data Index: 125425 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1326843 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1928. Min Act: -0.0000

Data Index: 954048 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2014. Min Act: -0.0000

Data Index: 36902 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1849. Min Act: -0.0001

Data Index: 318353 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1759. Min Act: -0.0000

Data Index: 722242 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1754. Min Act: -0.0000

Data Index: 41316 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2011. Min Act: -0.0000

Data Index: 118927 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1104091 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1790. Min Act: -0.0001

Data Index: 341734 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1916. Min Act: -0.0001

Data Index: 578968 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1536. Min Act: -0.0000

Data Index: 315234 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1756. Min Act: -0.0001

Data Index: 172212 (C4 (Web Text))

Max Activating Token Index: 144