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

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

Neuron 3812 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.9912. Min Act: -0.0000

Data Index: 353818 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1008199 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1009207 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1195635 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.8201. Min Act: -0.0001

Data Index: 1133699 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1052126 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7779. Min Act: -0.0001

Data Index: 839159 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1160686 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1072863 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7618. Min Act: -0.0000

Data Index: 37888 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1299321 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7524. Min Act: -0.0000

Data Index: 509640 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7025. Min Act: -0.0000

Data Index: 393647 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7346. Min Act: -0.0000

Data Index: 796140 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7481. Min Act: -0.0000

Data Index: 309517 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1105062 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1273902 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.7137. Min Act: -0.0000

Data Index: 150889 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.6925. Min Act: -0.0000

Data Index: 310787 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.9912. Min Range: -0.9912

Max Act: 0.6849. Min Act: -0.0000

Data Index: 51387 (C4 (Web Text))

Max Activating Token Index: 509