Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0919. Min Act: -0.0002

Data Index: 291486 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0856. Min Act: -0.0002

Data Index: 427083 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0856. Min Act: -0.0002

Data Index: 823382 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0810. Min Act: -0.0001

Data Index: 626887 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1175127 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1101179 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0811. Min Act: -0.0002

Data Index: 198932 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1273838 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0780. Min Act: -0.0002

Data Index: 475786 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0786. Min Act: -0.0002

Data Index: 709769 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0801. Min Act: -0.0002

Data Index: 656997 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1231253 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0777. Min Act: -0.0002

Data Index: 832570 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1144252 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0773. Min Act: -0.0002

Data Index: 580063 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0785. Min Act: -0.0002

Data Index: 822787 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0787. Min Act: -0.0002

Data Index: 445134 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0778. Min Act: -0.0002

Data Index: 729704 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0773. Min Act: -0.0001

Data Index: 763505 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0796. Min Act: -0.0002

Data Index: 131077 (C4 (Web Text))

Max Activating Token Index: 974