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

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

Neuron 1208 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1042. Min Range: -1.1042

Max Act: 1.1042. Min Act: -0.0001

Data Index: 220569 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9683. Min Act: -0.0001

Data Index: 75646 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 1.1042. Min Range: -1.1042

Max Act: 1.0251. Min Act: -0.0001

Data Index: 685081 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9822. Min Act: -0.0001

Data Index: 230846 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.1042. Min Range: -1.1042

Max Act: 1.0071. Min Act: -0.0001

Data Index: 738194 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9333. Min Act: -0.0001

Data Index: 437160 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9336. Min Act: -0.0001

Data Index: 413842 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9277. Min Act: -0.0001

Data Index: 731538 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9168. Min Act: -0.0001

Data Index: 40300 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9684. Min Act: -0.0001

Data Index: 688465 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.9327. Min Act: -0.0001

Data Index: 196679 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8813. Min Act: -0.0001

Data Index: 134164 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8765. Min Act: -0.0001

Data Index: 40882 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8129. Min Act: -0.0001

Data Index: 251318 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8914. Min Act: -0.0001

Data Index: 34600 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8925. Min Act: -0.0001

Data Index: 939433 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8670. Min Act: -0.0001

Data Index: 123710 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8565. Min Act: -0.0001

Data Index: 990182 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.8602. Min Act: -0.0001

Data Index: 913247 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.1042. Min Range: -1.1042

Max Act: 0.7865. Min Act: -0.0001

Data Index: 712742 (C4 (Web Text))

Max Activating Token Index: 825