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

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

Neuron 3500 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0001

Data Index: 456836 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0829. Min Act: -0.0001

Data Index: 787335 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1258630 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0947. Min Act: -0.0001

Data Index: 119176 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0814. Min Act: -0.0001

Data Index: 369264 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0867. Min Act: -0.0001

Data Index: 945288 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0769. Min Act: -0.0001

Data Index: 168834 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0753. Min Act: -0.0001

Data Index: 321895 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0792. Min Act: -0.0001

Data Index: 26333 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0939. Min Act: -0.0001

Data Index: 155704 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0844. Min Act: -0.0001

Data Index: 645623 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0805. Min Act: -0.0001

Data Index: 868082 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0845. Min Act: -0.0001

Data Index: 551996 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0708. Min Act: -0.0001

Data Index: 654068 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0789. Min Act: -0.0001

Data Index: 989826 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0812. Min Act: -0.0001

Data Index: 423492 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0778. Min Act: -0.0002

Data Index: 812322 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0725. Min Act: -0.0001

Data Index: 603906 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0744. Min Act: -0.0001

Data Index: 846226 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1233106 (C4 (Web Text))

Max Activating Token Index: 853