Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1726 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.6331. Min Act: -0.0000

Data Index: 94019 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.4784. Min Act: -0.0000

Data Index: 945774 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.5664. Min Act: -0.0000

Data Index: 365295 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1284841 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.3710. Min Act: -0.0000

Data Index: 395907 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1124445 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1223609 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.1697. Min Act: -0.0000

Data Index: 239967 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.2768. Min Act: -0.0000

Data Index: 164057 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.1775. Min Act: -0.0000

Data Index: 88084 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.2094. Min Act: -0.0000

Data Index: 610128 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.2154. Min Act: -0.0000

Data Index: 434738 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1049021 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.2060. Min Act: -0.0000

Data Index: 427518 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.1598. Min Act: -0.0000

Data Index: 743898 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.1297. Min Act: -0.0000

Data Index: 1099814 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.1733. Min Act: -0.0000

Data Index: 803696 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.1427. Min Act: -0.0000

Data Index: 933088 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.0806. Min Act: -0.0000

Data Index: 129350 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 1.6331. Min Range: -1.6331

Max Act: 1.0785. Min Act: -0.0000

Data Index: 281173 (C4 (Web Text))

Max Activating Token Index: 905