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

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

Neuron 5912 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5678. Min Range: -2.5678

Max Act: 2.5678. Min Act: -0.0000

Data Index: 407400 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 2.5678. Min Range: -2.5678

Max Act: 2.2713. Min Act: -0.0000

Data Index: 293306 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 2.5678. Min Range: -2.5678

Max Act: 2.2716. Min Act: -0.0000

Data Index: 529415 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.9973. Min Act: -0.0000

Data Index: 734854 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 2.5678. Min Range: -2.5678

Max Act: 2.2143. Min Act: -0.0000

Data Index: 829546 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.9372. Min Act: -0.0000

Data Index: 719589 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.9166. Min Act: -0.0000

Data Index: 871496 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 2.5678. Min Range: -2.5678

Max Act: 2.0192. Min Act: 0.0000

Data Index: 615494 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.8946. Min Act: -0.0000

Data Index: 361241 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.8838. Min Act: 0.0000

Data Index: 714243 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.8525. Min Act: -0.0000

Data Index: 879854 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.8090. Min Act: -0.0000

Data Index: 522326 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.9198. Min Act: -0.0000

Data Index: 756117 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.7853. Min Act: -0.0000

Data Index: 336998 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.7871. Min Act: -0.0000

Data Index: 981076 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.8770. Min Act: -0.0000

Data Index: 1243251 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.7718. Min Act: -0.0000

Data Index: 16197 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.7605. Min Act: -0.0000

Data Index: 749236 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.8405. Min Act: -0.0000

Data Index: 467213 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 2.5678. Min Range: -2.5678

Max Act: 1.7459. Min Act: -0.0000

Data Index: 76849 (C4 (Web Text))

Max Activating Token Index: 570