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

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

Neuron 1630 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.5924. Min Act: -0.0000

Data Index: 1098564 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.5684. Min Act: -0.0000

Data Index: 78045 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.3871. Min Act: -0.0000

Data Index: 831289 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.3533. Min Act: -0.0000

Data Index: 653796 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.2649. Min Act: 0.0000

Data Index: 791225 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.3352. Min Act: -0.0000

Data Index: 184923 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.2218. Min Act: -0.0000

Data Index: 623187 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.2248. Min Act: -0.0000

Data Index: 64448 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.1966. Min Act: -0.0000

Data Index: 1071002 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.3497. Min Act: -0.0000

Data Index: 975849 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1090145 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.2272. Min Act: -0.0000

Data Index: 744644 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1027044 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.1811. Min Act: -0.0000

Data Index: 495592 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.1103. Min Act: -0.0000

Data Index: 282137 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.1597. Min Act: -0.0000

Data Index: 487831 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.0918. Min Act: 0.0000

Data Index: 956099 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.1524. Min Act: -0.0000

Data Index: 955352 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.2300. Min Act: -0.0000

Data Index: 592006 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 1.5924. Min Range: -1.5924

Max Act: 1.1592. Min Act: -0.0000

Data Index: 412923 (C4 (Web Text))

Max Activating Token Index: 702