Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1657 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.9680. Min Act: -0.0001

Data Index: 652725 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8422. Min Act: -0.0001

Data Index: 39498 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.9096. Min Act: -0.0001

Data Index: 299372 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8577. Min Act: -0.0001

Data Index: 405742 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7914. Min Act: -0.0001

Data Index: 474630 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8334. Min Act: -0.0001

Data Index: 1066356 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7525. Min Act: -0.0001

Data Index: 259040 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7793. Min Act: -0.0001

Data Index: 186665 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7032. Min Act: -0.0001

Data Index: 248260 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7396. Min Act: -0.0001

Data Index: 1114378 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7999. Min Act: -0.0001

Data Index: 1134815 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7447. Min Act: -0.0001

Data Index: 159216 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7140. Min Act: -0.0001

Data Index: 243792 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7196. Min Act: -0.0001

Data Index: 850283 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7127. Min Act: -0.0001

Data Index: 1146941 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7036. Min Act: -0.0001

Data Index: 814663 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6683. Min Act: -0.0001

Data Index: 827714 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7040. Min Act: -0.0001

Data Index: 779757 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6758. Min Act: -0.0001

Data Index: 325389 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6677. Min Act: -0.0001

Data Index: 619417 (C4 (Web Text))

Max Activating Token Index: 198