Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1002674 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0857. Min Act: -0.0000

Data Index: 444863 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0820. Min Act: -0.0001

Data Index: 799490 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0853. Min Act: -0.0000

Data Index: 74205 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0709. Min Act: -0.0001

Data Index: 40143 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0741. Min Act: -0.0000

Data Index: 1305490 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0727. Min Act: -0.0001

Data Index: 570356 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1179544 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0690. Min Act: -0.0000

Data Index: 390440 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0680. Min Act: -0.0000

Data Index: 1031288 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1504239 (Python Code)

Max Activating Token Index: 678

Text #11

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0669. Min Act: -0.0000

Data Index: 470858 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1286634 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0628. Min Act: -0.0000

Data Index: 282738 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0660. Min Act: -0.0000

Data Index: 67721 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0664. Min Act: -0.0001

Data Index: 754030 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0580. Min Act: -0.0000

Data Index: 397095 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0633. Min Act: -0.0001

Data Index: 797678 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0631. Min Act: -0.0000

Data Index: 44594 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1095244 (C4 (Web Text))

Max Activating Token Index: 831