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

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

Neuron 151 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0869. Min Act: -0.0000

Data Index: 812853 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1251. Min Act: -0.0000

Data Index: 566934 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0921. Min Act: -0.0000

Data Index: 843825 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0878. Min Act: -0.0000

Data Index: 512862 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0831. Min Act: -0.0000

Data Index: 295736 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1099991 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0773. Min Act: -0.0000

Data Index: 882991 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0800. Min Act: -0.0000

Data Index: 381070 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1154789 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0781. Min Act: -0.0000

Data Index: 891687 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0751. Min Act: -0.0000

Data Index: 612811 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1070734 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0669. Min Act: -0.0000

Data Index: 987157 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0643. Min Act: -0.0000

Data Index: 61199 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0616. Min Act: -0.0000

Data Index: 455554 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0684. Min Act: -0.0000

Data Index: 903126 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0653. Min Act: -0.0000

Data Index: 780412 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0677. Min Act: -0.0000

Data Index: 1074720 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0651. Min Act: -0.0000

Data Index: 784481 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0775. Min Act: -0.0000

Data Index: 103637 (C4 (Web Text))

Max Activating Token Index: 582