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

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

Neuron 4772 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2813. Min Act: -0.0000

Data Index: 601480 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2021. Min Act: -0.0000

Data Index: 380387 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2294. Min Act: -0.0000

Data Index: 183965 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1013. Min Act: -0.0000

Data Index: 422466 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0951. Min Act: -0.0000

Data Index: 519443 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0890. Min Act: -0.0000

Data Index: 421165 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0826. Min Act: -0.0000

Data Index: 922679 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0733. Min Act: -0.0000

Data Index: 330643 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0962. Min Act: -0.0000

Data Index: 257401 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0863. Min Act: -0.0000

Data Index: 957942 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0615. Min Act: -0.0000

Data Index: 228816 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1214700 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0133. Min Act: -0.0000

Data Index: 244648 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1108879 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9768. Min Act: -0.0000

Data Index: 842381 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1311261 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1151842 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0217. Min Act: -0.0000

Data Index: 545592 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9736. Min Act: -0.0000

Data Index: 668670 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9291. Min Act: -0.0000

Data Index: 167256 (C4 (Web Text))

Max Activating Token Index: 133