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

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

Neuron 749 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: 1.6908. Min Range: -1.6908

Max Act: 1.6908. Min Act: -0.0000

Data Index: 908023 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.5498. Min Act: -0.0000

Data Index: 538948 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.5200. Min Act: -0.0000

Data Index: 389181 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.3718. Min Act: -0.0000

Data Index: 735152 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.0914. Min Act: -0.0000

Data Index: 296678 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 1.6908. Min Range: -1.6908

Max Act: 1.0218. Min Act: -0.0000

Data Index: 630793 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1071991 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.9373. Min Act: -0.0000

Data Index: 648981 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.9426. Min Act: -0.0000

Data Index: 276001 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8588. Min Act: -0.0000

Data Index: 502802 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8828. Min Act: -0.0000

Data Index: 790805 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8822. Min Act: -0.0000

Data Index: 136405 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1356998 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8558. Min Act: -0.0000

Data Index: 171588 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8602. Min Act: -0.0000

Data Index: 700757 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8535. Min Act: -0.0000

Data Index: 828388 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8491. Min Act: 0.0000

Data Index: 667219 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1278898 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8252. Min Act: 0.0000

Data Index: 1208256 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.6908. Min Range: -1.6908

Max Act: 0.8138. Min Act: -0.0000

Data Index: 765126 (C4 (Web Text))

Max Activating Token Index: 875