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

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

Neuron 1002 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: 0.0828. Min Range: -0.0828

Max Act: 0.0828. Min Act: -0.0005

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0816. Min Act: -0.0005

Data Index: 872525 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0759. Min Act: -0.0005

Data Index: 1566267 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0711. Min Act: -0.0005

Data Index: 1510173 (Python Code)

Max Activating Token Index: 880

Text #4

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0733. Min Act: -0.0006

Data Index: 1007764 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0689. Min Act: -0.0006

Data Index: 573328 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0717. Min Act: -0.0006

Data Index: 657002 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0712. Min Act: -0.0006

Data Index: 470388 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0704. Min Act: -0.0006

Data Index: 316661 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0686. Min Act: -0.0006

Data Index: 776622 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0656. Min Act: -0.0005

Data Index: 1060530 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0684. Min Act: -0.0005

Data Index: 354452 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0665. Min Act: -0.0006

Data Index: 1307645 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0625. Min Act: -0.0006

Data Index: 806408 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0647. Min Act: -0.0005

Data Index: 1319498 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0614. Min Act: -0.0006

Data Index: 1484513 (Python Code)

Max Activating Token Index: 277

Text #16

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0663. Min Act: -0.0006

Data Index: 960268 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0635. Min Act: -0.0006

Data Index: 1518204 (Python Code)

Max Activating Token Index: 234

Text #18

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0661. Min Act: -0.0006

Data Index: 765499 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0621. Min Act: -0.0006

Data Index: 743083 (C4 (Web Text))

Max Activating Token Index: 86