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

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

Neuron 337 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.1470. Min Act: -0.0000

Data Index: 397984 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.1150. Min Act: -0.0000

Data Index: 96015 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1432226 (Python Code)

Max Activating Token Index: 749

Text #3

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1249009 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1436524 (Python Code)

Max Activating Token Index: 618

Text #5

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.1001. Min Act: -0.0000

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0980. Min Act: -0.0000

Data Index: 646401 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1149889 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0996. Min Act: -0.0000

Data Index: 574728 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1430438 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0801. Min Act: -0.0000

Data Index: 409032 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0880. Min Act: -0.0000

Data Index: 674704 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0943. Min Act: -0.0000

Data Index: 380230 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0870. Min Act: -0.0000

Data Index: 679682 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1013965 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1301783 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0857. Min Act: -0.0000

Data Index: 865395 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0857. Min Act: -0.0000

Data Index: 947578 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1536467 (Python Code)

Max Activating Token Index: 770

Text #19

Max Range: 0.1470. Min Range: -0.1470

Max Act: 0.0767. Min Act: -0.0000

Data Index: 284655 (C4 (Web Text))

Max Activating Token Index: 731