Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1130 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2308. Min Act: -0.0003

Data Index: 789096 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2020. Min Act: -0.0003

Data Index: 336228 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1954. Min Act: -0.0003

Data Index: 171902 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1765. Min Act: -0.0003

Data Index: 596992 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1581. Min Act: -0.0003

Data Index: 34315 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1812. Min Act: -0.0003

Data Index: 956940 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1823. Min Act: -0.0003

Data Index: 882127 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1749. Min Act: -0.0003

Data Index: 657640 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1802. Min Act: -0.0003

Data Index: 46806 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1730. Min Act: -0.0003

Data Index: 1330275 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1793. Min Act: -0.0003

Data Index: 571393 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1673. Min Act: -0.0003

Data Index: 721580 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1625. Min Act: -0.0003

Data Index: 958679 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1620. Min Act: -0.0003

Data Index: 253900 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1622. Min Act: -0.0003

Data Index: 579944 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1733. Min Act: -0.0003

Data Index: 600314 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1593. Min Act: -0.0003

Data Index: 101545 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1710. Min Act: -0.0003

Data Index: 193672 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1704. Min Act: -0.0003

Data Index: 832063 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1589. Min Act: -0.0003

Data Index: 844233 (C4 (Web Text))

Max Activating Token Index: 216