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

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

Neuron 2637 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.8493. Min Act: -0.0000

Data Index: 535525 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1092660 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7487. Min Act: -0.0000

Data Index: 130778 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.6733. Min Act: -0.0000

Data Index: 59372 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.8021. Min Act: -0.0000

Data Index: 420953 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1025253 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.8088. Min Act: -0.0000

Data Index: 941155 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7804. Min Act: -0.0000

Data Index: 495653 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7152. Min Act: -0.0000

Data Index: 743614 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7449. Min Act: -0.0000

Data Index: 837085 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7627. Min Act: -0.0000

Data Index: 751857 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7159. Min Act: -0.0000

Data Index: 901193 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1330093 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.6919. Min Act: -0.0000

Data Index: 888132 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1018180 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7437. Min Act: -0.0000

Data Index: 142690 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1056560 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7142. Min Act: -0.0000

Data Index: 467736 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1032624 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.8493. Min Range: -0.8493

Max Act: 0.7590. Min Act: -0.0000

Data Index: 791067 (C4 (Web Text))

Max Activating Token Index: 485