Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 28 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0763. Min Act: -0.0003

Data Index: 25060 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0770. Min Act: -0.0003

Data Index: 353937 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0750. Min Act: -0.0003

Data Index: 90096 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0775. Min Act: -0.0004

Data Index: 661999 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0754. Min Act: -0.0003

Data Index: 227433 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0777. Min Act: -0.0003

Data Index: 156106 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0730. Min Act: -0.0003

Data Index: 400051 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0747. Min Act: -0.0003

Data Index: 477969 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1326647 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0753. Min Act: -0.0002

Data Index: 474619 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0741. Min Act: -0.0003

Data Index: 758221 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0742. Min Act: -0.0003

Data Index: 664908 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0735. Min Act: -0.0003

Data Index: 310099 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0766. Min Act: -0.0003

Data Index: 785149 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0731. Min Act: -0.0004

Data Index: 702570 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0757. Min Act: -0.0003

Data Index: 1155229 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0744. Min Act: -0.0003

Data Index: 922189 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0728. Min Act: -0.0003

Data Index: 662470 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0737. Min Act: -0.0004

Data Index: 61673 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1037181 (C4 (Web Text))

Max Activating Token Index: 113