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

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

Neuron 4264 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2950. Min Act: -0.0000

Data Index: 233157 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1194022 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2344. Min Act: -0.0000

Data Index: 74487 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1330665 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1978. Min Act: -0.0000

Data Index: 534121 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1980. Min Act: -0.0000

Data Index: 609110 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1811. Min Act: -0.0000

Data Index: 832553 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1860. Min Act: -0.0000

Data Index: 968433 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1791. Min Act: -0.0000

Data Index: 8244 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1811. Min Act: -0.0000

Data Index: 2486 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1808. Min Act: -0.0000

Data Index: 826826 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1867. Min Act: -0.0000

Data Index: 809672 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1852. Min Act: -0.0000

Data Index: 317818 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1787. Min Act: -0.0000

Data Index: 768714 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1720. Min Act: -0.0000

Data Index: 787767 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1828. Min Act: -0.0000

Data Index: 483225 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1744. Min Act: -0.0000

Data Index: 400810 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1812. Min Act: -0.0000

Data Index: 791670 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1160591 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1575. Min Act: -0.0000

Data Index: 300659 (C4 (Web Text))

Max Activating Token Index: 97