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

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

Neuron 3560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.1035. Min Act: -0.0002

Data Index: 269960 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0973. Min Act: -0.0002

Data Index: 697466 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1092281 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0678. Min Act: -0.0002

Data Index: 671159 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0813. Min Act: -0.0002

Data Index: 621122 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1325513 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0789. Min Act: -0.0002

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0857. Min Act: -0.0002

Data Index: 441737 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0859. Min Act: -0.0002

Data Index: 935738 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0802. Min Act: -0.0002

Data Index: 49409 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0809. Min Act: -0.0002

Data Index: 942212 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0819. Min Act: -0.0002

Data Index: 143863 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0807. Min Act: -0.0002

Data Index: 991969 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0736. Min Act: -0.0002

Data Index: 15872 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0720. Min Act: -0.0002

Data Index: 677095 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0815. Min Act: -0.0002

Data Index: 347368 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0835. Min Act: -0.0002

Data Index: 141056 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1337070 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0838. Min Act: -0.0002

Data Index: 101775 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0742. Min Act: -0.0002

Data Index: 535614 (C4 (Web Text))

Max Activating Token Index: 833