Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1554 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0999. Min Act: -0.0002

Data Index: 146744 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0893. Min Act: -0.0001

Data Index: 686742 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0895. Min Act: -0.0002

Data Index: 815199 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0836. Min Act: -0.0001

Data Index: 667243 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1165930 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1164236 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0625. Min Act: -0.0001

Data Index: 440017 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0698. Min Act: -0.0001

Data Index: 850293 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0598. Min Act: -0.0001

Data Index: 685991 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0642. Min Act: -0.0001

Data Index: 354305 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1206929 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0695. Min Act: -0.0001

Data Index: 9574 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0636. Min Act: -0.0001

Data Index: 264476 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1289543 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0620. Min Act: -0.0001

Data Index: 961302 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1180210 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0631. Min Act: -0.0001

Data Index: 361628 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1133451 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0645. Min Act: -0.0001

Data Index: 383804 (C4 (Web Text))

Max Activating Token Index: 438