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

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

Neuron 1919 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0871. Min Range: -4.0871

Max Act: 4.0871. Min Act: -0.0002

Data Index: 1311417 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9845. Min Act: -0.0002

Data Index: 770795 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 4.0871. Min Range: -4.0871

Max Act: 4.0724. Min Act: -0.0002

Data Index: 1159484 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.7902. Min Act: -0.0002

Data Index: 620362 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.8759. Min Act: -0.0002

Data Index: 166037 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.6700. Min Act: -0.0002

Data Index: 944225 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.4062. Min Act: -0.0002

Data Index: 128791 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.3313. Min Act: -0.0002

Data Index: 536175 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.3612. Min Act: -0.0002

Data Index: 1130815 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.4643. Min Act: -0.0002

Data Index: 1051745 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 4.0871. Min Range: -4.0871

Max Act: 2.9996. Min Act: -0.0002

Data Index: 876098 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.4036. Min Act: -0.0002

Data Index: 954132 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.5382. Min Act: -0.0002

Data Index: 1077010 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.4808. Min Act: -0.0002

Data Index: 844994 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.1826. Min Act: -0.0002

Data Index: 605062 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.2979. Min Act: -0.0002

Data Index: 525984 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.2616. Min Act: -0.0002

Data Index: 1059358 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.1193. Min Act: -0.0002

Data Index: 1167733 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 4.0871. Min Range: -4.0871

Max Act: 2.9822. Min Act: -0.0002

Data Index: 1020158 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.1700. Min Act: -0.0002

Data Index: 416590 (C4 (Web Text))

Max Activating Token Index: 155