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

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

Neuron 3370 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: 0.3706. Min Range: -0.3706

Max Act: 0.3706. Min Act: -0.0001

Data Index: 312614 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1031541 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2998. Min Act: -0.0001

Data Index: 1045274 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.3117. Min Act: -0.0001

Data Index: 736529 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.3195. Min Act: -0.0001

Data Index: 843673 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2813. Min Act: -0.0001

Data Index: 1132574 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2815. Min Act: -0.0001

Data Index: 402446 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2999. Min Act: -0.0001

Data Index: 216979 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.3080. Min Act: -0.0001

Data Index: 638508 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2980. Min Act: -0.0001

Data Index: 1214296 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2941. Min Act: -0.0001

Data Index: 235486 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2877. Min Act: -0.0001

Data Index: 1329308 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2870. Min Act: -0.0001

Data Index: 460584 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2503. Min Act: -0.0001

Data Index: 943424 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2852. Min Act: -0.0001

Data Index: 1000988 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2820. Min Act: -0.0001

Data Index: 992037 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2555. Min Act: -0.0001

Data Index: 87300 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2831. Min Act: -0.0001

Data Index: 954783 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2721. Min Act: -0.0001

Data Index: 1038119 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.3706. Min Range: -0.3706

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1022467 (C4 (Web Text))

Max Activating Token Index: 771