Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1054 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0005

Data Index: 930757 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0853. Min Act: -0.0005

Data Index: 503267 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0840. Min Act: -0.0006

Data Index: 342585 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0818. Min Act: -0.0005

Data Index: 436269 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0818. Min Act: -0.0006

Data Index: 186337 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0789. Min Act: -0.0006

Data Index: 635388 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0775. Min Act: -0.0005

Data Index: 1066443 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0738. Min Act: -0.0005

Data Index: 902384 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0810. Min Act: -0.0006

Data Index: 134157 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0768. Min Act: -0.0006

Data Index: 1181362 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0760. Min Act: -0.0006

Data Index: 865046 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0771. Min Act: -0.0005

Data Index: 444083 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0785. Min Act: -0.0005

Data Index: 146942 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0770. Min Act: -0.0006

Data Index: 751196 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0743. Min Act: -0.0006

Data Index: 464546 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0711. Min Act: -0.0005

Data Index: 65461 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0710. Min Act: -0.0005

Data Index: 1310505 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0706. Min Act: -0.0005

Data Index: 582307 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0715. Min Act: -0.0006

Data Index: 127508 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0730. Min Act: -0.0006

Data Index: 956638 (C4 (Web Text))

Max Activating Token Index: 986