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

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

Neuron 3793 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2331. Min Act: -0.0000

Data Index: 716935 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1622891 (Python Code)

Max Activating Token Index: 283

Text #2

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1421802 (Python Code)

Max Activating Token Index: 299

Text #3

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1146967 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2024. Min Act: -0.0000

Data Index: 261398 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1927. Min Act: -0.0000

Data Index: 963641 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1064201 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2104. Min Act: -0.0000

Data Index: 865111 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1184386 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1175162 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1621112 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1812. Min Act: -0.0000

Data Index: 359331 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2068. Min Act: -0.0000

Data Index: 330993 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1959. Min Act: -0.0000

Data Index: 525891 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1155928 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1448683 (Python Code)

Max Activating Token Index: 546

Text #16

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1627. Min Act: -0.0000

Data Index: 232047 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1742. Min Act: -0.0000

Data Index: 45709 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1200417 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1752. Min Act: -0.0000

Data Index: 714510 (C4 (Web Text))

Max Activating Token Index: 137