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

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

Neuron 2177 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0531. Min Range: -1.0531

Max Act: 1.0531. Min Act: -0.0000

Data Index: 818779 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.9927. Min Act: -0.0000

Data Index: 621712 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1233576 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.7716. Min Act: -0.0000

Data Index: 188706 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.7366. Min Act: -0.0000

Data Index: 727330 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6471. Min Act: -0.0000

Data Index: 969686 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1150398 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1291711 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1338974 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6039. Min Act: -0.0000

Data Index: 141139 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6150. Min Act: -0.0000

Data Index: 191836 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1071661 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6150. Min Act: -0.0000

Data Index: 587280 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1005458 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1058558 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.5520. Min Act: -0.0000

Data Index: 218999 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1042147 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.6367. Min Act: -0.0000

Data Index: 622004 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1079091 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1295880 (C4 (Web Text))

Max Activating Token Index: 777