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

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

Neuron 3488 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.5783. Min Act: -0.0000

Data Index: 13800 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3754. Min Act: 0.0001

Data Index: 491342 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.4928. Min Act: -0.0000

Data Index: 1248906 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3785. Min Act: 0.0001

Data Index: 522212 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.5117. Min Act: -0.0000

Data Index: 1268135 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.4258. Min Act: 0.0001

Data Index: 571660 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3626. Min Act: 0.0000

Data Index: 1037135 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3040. Min Act: 0.0001

Data Index: 1000932 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3816. Min Act: 0.0001

Data Index: 531356 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3152. Min Act: -0.0000

Data Index: 719913 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3351. Min Act: -0.0000

Data Index: 643227 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3330. Min Act: 0.0001

Data Index: 979497 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.2888. Min Act: 0.0001

Data Index: 319684 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.2922. Min Act: 0.0001

Data Index: 756854 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.2766. Min Act: 0.0001

Data Index: 1214222 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.2692. Min Act: -0.0000

Data Index: 476302 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.2670. Min Act: 0.0002

Data Index: 914579 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.2764. Min Act: 0.0000

Data Index: 287700 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.3025. Min Act: 0.0001

Data Index: 956134 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.5783. Min Range: -1.5783

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1344510 (C4 (Web Text))

Max Activating Token Index: 720