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

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

Neuron 4596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.9357. Min Act: -0.0000

Data Index: 691900 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.4461. Min Act: -0.0000

Data Index: 1218637 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.3987. Min Act: -0.0000

Data Index: 833385 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.1664. Min Act: -0.0000

Data Index: 855281 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.3564. Min Act: -0.0000

Data Index: 434499 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.0207. Min Act: -0.0000

Data Index: 470422 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.0039. Min Act: -0.0000

Data Index: 519915 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.0682. Min Act: -0.0000

Data Index: 802647 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 2.9357. Min Range: -2.9357

Max Act: 1.7779. Min Act: -0.0000

Data Index: 810486 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.1678. Min Act: -0.0000

Data Index: 12801 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.0732. Min Act: -0.0000

Data Index: 1309546 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.0219. Min Act: -0.0000

Data Index: 692037 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1073168 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 2.9357. Min Range: -2.9357

Max Act: 1.8321. Min Act: -0.0000

Data Index: 392955 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 2.9357. Min Range: -2.9357

Max Act: 1.9149. Min Act: -0.0000

Data Index: 944005 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 2.9357. Min Range: -2.9357

Max Act: 2.0184. Min Act: -0.0000

Data Index: 744729 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 2.9357. Min Range: -2.9357

Max Act: 1.7150. Min Act: -0.0000

Data Index: 811519 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 2.9357. Min Range: -2.9357

Max Act: 1.9017. Min Act: -0.0000

Data Index: 851631 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.9357. Min Range: -2.9357

Max Act: 1.9109. Min Act: -0.0000

Data Index: 1042879 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 2.9357. Min Range: -2.9357

Max Act: 1.7850. Min Act: -0.0000

Data Index: 689272 (C4 (Web Text))

Max Activating Token Index: 285