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

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

Neuron 3694 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: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0001

Data Index: 41083 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1169503 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1196068 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0796. Min Act: -0.0001

Data Index: 264087 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0715. Min Act: -0.0001

Data Index: 398952 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1121085 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1046524 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0740. Min Act: -0.0001

Data Index: 717523 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0717. Min Act: -0.0001

Data Index: 367621 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0683. Min Act: -0.0001

Data Index: 140910 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1147590 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0674. Min Act: -0.0001

Data Index: 233808 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1101768 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0711. Min Act: -0.0001

Data Index: 359032 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0664. Min Act: -0.0001

Data Index: 487436 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0672. Min Act: -0.0001

Data Index: 29906 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0689. Min Act: -0.0001

Data Index: 319571 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1112566 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0610. Min Act: -0.0001

Data Index: 819622 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1504560 (Python Code)

Max Activating Token Index: 187