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

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

Neuron 814 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: 0.2327. Min Range: -0.2327

Max Act: 0.2327. Min Act: 0.0000

Data Index: 1382731 (Python Code)

Max Activating Token Index: 192

Text #1

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1411395 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2244. Min Act: -0.0000

Data Index: 568143 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1569127 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2073. Min Act: 0.0000

Data Index: 1386812 (Python Code)

Max Activating Token Index: 481

Text #5

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2216. Min Act: -0.0000

Data Index: 4445 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1633225 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1545762 (Python Code)

Max Activating Token Index: 946

Text #8

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1858. Min Act: -0.0000

Data Index: 880379 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2037. Min Act: -0.0000

Data Index: 434324 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1099333 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1910. Min Act: -0.0000

Data Index: 230252 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1509457 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1586505 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1904. Min Act: -0.0000

Data Index: 737723 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1548960 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1533749 (Python Code)

Max Activating Token Index: 956

Text #17

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1824. Min Act: -0.0000

Data Index: 394011 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1390371 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1741. Min Act: -0.0000

Data Index: 882356 (C4 (Web Text))

Max Activating Token Index: 270