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

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

Neuron 4818 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3780. Min Act: -0.0000

Data Index: 108168 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3389. Min Act: -0.0000

Data Index: 268502 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3211. Min Act: -0.0000

Data Index: 431196 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3166. Min Act: -0.0000

Data Index: 703870 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3145. Min Act: -0.0000

Data Index: 474106 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1090327 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2919. Min Act: -0.0000

Data Index: 89807 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2693. Min Act: -0.0000

Data Index: 608233 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2741. Min Act: -0.0000

Data Index: 100920 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2819. Min Act: -0.0000

Data Index: 163187 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2722. Min Act: -0.0000

Data Index: 681297 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1093633 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2913. Min Act: -0.0000

Data Index: 910944 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1010663 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2850. Min Act: -0.0000

Data Index: 85529 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2724. Min Act: -0.0000

Data Index: 630474 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2613. Min Act: -0.0000

Data Index: 306923 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1228592 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2651. Min Act: -0.0000

Data Index: 406776 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2552. Min Act: -0.0000

Data Index: 504519 (C4 (Web Text))

Max Activating Token Index: 211