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

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

Neuron 5135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.9035. Min Act: -0.0000

Data Index: 162717 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.9568. Min Act: -0.0000

Data Index: 399194 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.2853. Min Act: -0.0000

Data Index: 704293 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.2733. Min Act: -0.0000

Data Index: 811961 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.2037. Min Act: -0.0000

Data Index: 1283832 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.0615. Min Act: -0.0000

Data Index: 1274027 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.0634. Min Act: -0.0000

Data Index: 1231444 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.1339. Min Act: -0.0000

Data Index: 344566 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.1006. Min Act: -0.0000

Data Index: 1262066 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.9585. Min Act: -0.0000

Data Index: 292210 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.0802. Min Act: -0.0000

Data Index: 1006941 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.9513. Min Act: -0.0000

Data Index: 1231480 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 2.9568. Min Range: -2.9568

Max Act: 2.0718. Min Act: -0.0000

Data Index: 1052601 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.8500. Min Act: -0.0000

Data Index: 897826 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.7499. Min Act: -0.0000

Data Index: 703665 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.9007. Min Act: -0.0000

Data Index: 432156 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.7839. Min Act: -0.0000

Data Index: 507627 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.9923. Min Act: -0.0000

Data Index: 621180 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.7963. Min Act: -0.0000

Data Index: 108434 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 2.9568. Min Range: -2.9568

Max Act: 1.9840. Min Act: -0.0000

Data Index: 373733 (C4 (Web Text))

Max Activating Token Index: 942