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

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

Neuron 5528 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: 1.1895. Min Range: -1.1895

Max Act: 1.0672. Min Act: -0.0000

Data Index: 448437 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.1895. Min Range: -1.1895

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1129161 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 1.1895. Min Range: -1.1895

Max Act: 1.0912. Min Act: -0.0000

Data Index: 735191 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.1895. Min Range: -1.1895

Max Act: 1.1165. Min Act: -0.0000

Data Index: 218845 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.9895. Min Act: -0.0000

Data Index: 546693 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.9745. Min Act: -0.0000

Data Index: 431920 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.9544. Min Act: -0.0000

Data Index: 181578 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.9131. Min Act: -0.0000

Data Index: 49239 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.9447. Min Act: -0.0000

Data Index: 457303 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.8741. Min Act: -0.0000

Data Index: 220826 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.8777. Min Act: -0.0000

Data Index: 66751 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1594785 (Python Code)

Max Activating Token Index: 603

Text #12

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7869. Min Act: -0.0000

Data Index: 222589 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7452. Min Act: -0.0000

Data Index: 210038 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7631. Min Act: -0.0000

Data Index: 539564 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1632120 (Python Code)

Max Activating Token Index: 278

Text #16

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1482167 (Python Code)

Max Activating Token Index: 259

Text #17

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.7083. Min Act: -0.0000

Data Index: 480913 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1399676 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 1.1895. Min Range: -1.1895

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1556117 (Python Code)

Max Activating Token Index: 590