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

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

Neuron 4361 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.9183. Min Act: -0.0000

Data Index: 1085915 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.9636. Min Act: -0.0000

Data Index: 508601 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.8288. Min Act: -0.0000

Data Index: 882599 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.8995. Min Act: -0.0000

Data Index: 850703 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.8672. Min Act: -0.0000

Data Index: 557958 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.8430. Min Act: -0.0000

Data Index: 467377 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.7840. Min Act: -0.0000

Data Index: 683109 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.7859. Min Act: -0.0000

Data Index: 140896 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.7359. Min Act: -0.0000

Data Index: 465488 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.7383. Min Act: -0.0000

Data Index: 1145895 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.7299. Min Act: -0.0000

Data Index: 591016 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.7144. Min Act: -0.0000

Data Index: 885677 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.6207. Min Act: -0.0000

Data Index: 1122014 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.6867. Min Act: -0.0000

Data Index: 202262 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.7759. Min Act: -0.0000

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.6834. Min Act: -0.0000

Data Index: 1186097 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.6722. Min Act: -0.0000

Data Index: 506543 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.6700. Min Act: -0.0000

Data Index: 783211 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1310732 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 1.9636. Min Range: -1.9636

Max Act: 1.6624. Min Act: -0.0000

Data Index: 777393 (C4 (Web Text))

Max Activating Token Index: 691