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

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

Neuron 2667 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: 4.9031. Min Range: -4.9031

Max Act: 4.9031. Min Act: -0.0000

Data Index: 1035918 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.4393. Min Act: -0.0000

Data Index: 255171 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.1588. Min Act: -0.0000

Data Index: 403765 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.1360. Min Act: -0.0000

Data Index: 863677 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.3006. Min Act: -0.0000

Data Index: 608990 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.8232. Min Act: -0.0000

Data Index: 783587 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.8278. Min Act: -0.0000

Data Index: 1120840 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.1595. Min Act: -0.0000

Data Index: 667894 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.9783. Min Act: -0.0000

Data Index: 1010584 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.1172. Min Act: -0.0000

Data Index: 1316314 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.2603. Min Act: -0.0000

Data Index: 139338 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.0055. Min Act: -0.0000

Data Index: 36305 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.1688. Min Act: -0.0000

Data Index: 1250182 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.6529. Min Act: -0.0000

Data Index: 18324 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.9890. Min Act: -0.0000

Data Index: 129794 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.9845. Min Act: -0.0000

Data Index: 1129874 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.9797. Min Act: -0.0000

Data Index: 96154 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.4839. Min Act: -0.0000

Data Index: 1345416 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 4.9031. Min Range: -4.9031

Max Act: 4.1391. Min Act: -0.0000

Data Index: 992171 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 4.9031. Min Range: -4.9031

Max Act: 3.9315. Min Act: -0.0000

Data Index: 1082570 (C4 (Web Text))

Max Activating Token Index: 598