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

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

Neuron 3280 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: 0.0909. Min Range: -0.0909

Max Act: 0.0909. Min Act: -0.0001

Data Index: 722007 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0868. Min Act: -0.0001

Data Index: 357047 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0774. Min Act: -0.0001

Data Index: 887103 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0804. Min Act: -0.0001

Data Index: 796072 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1146552 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0760. Min Act: -0.0001

Data Index: 820230 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0845. Min Act: -0.0001

Data Index: 830844 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0788. Min Act: -0.0001

Data Index: 357311 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0749. Min Act: -0.0001

Data Index: 230638 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1213507 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0690. Min Act: -0.0001

Data Index: 342072 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0712. Min Act: -0.0001

Data Index: 431766 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0738. Min Act: -0.0001

Data Index: 615264 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1354551 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1229039 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1595480 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0680. Min Act: -0.0001

Data Index: 513696 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0721. Min Act: -0.0001

Data Index: 453995 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0687. Min Act: -0.0001

Data Index: 899973 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0727. Min Act: -0.0001

Data Index: 687637 (C4 (Web Text))

Max Activating Token Index: 977