Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4403 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1005916 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0806. Min Act: -0.0001

Data Index: 800885 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0758. Min Act: -0.0001

Data Index: 695594 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0759. Min Act: -0.0001

Data Index: 923954 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1237155 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0001

Data Index: 38393 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0779. Min Act: -0.0001

Data Index: 733603 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1059263 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0729. Min Act: -0.0001

Data Index: 32915 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0730. Min Act: -0.0001

Data Index: 301670 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0687. Min Act: -0.0001

Data Index: 74454 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0675. Min Act: -0.0001

Data Index: 1064843 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1043167 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0635. Min Act: -0.0001

Data Index: 790819 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0686. Min Act: -0.0001

Data Index: 550754 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0724. Min Act: -0.0001

Data Index: 252510 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0672. Min Act: -0.0001

Data Index: 334852 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0675. Min Act: -0.0001

Data Index: 801086 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0686. Min Act: -0.0001

Data Index: 287242 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1013484 (C4 (Web Text))

Max Activating Token Index: 529