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

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

Neuron 3488 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1698. Min Act: -0.0001

Data Index: 422245 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1419. Min Act: -0.0001

Data Index: 278222 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1159. Min Act: -0.0001

Data Index: 766946 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0996. Min Act: -0.0000

Data Index: 350315 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0966. Min Act: -0.0001

Data Index: 573693 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1399284 (Python Code)

Max Activating Token Index: 855

Text #6

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1425615 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0854. Min Act: -0.0001

Data Index: 831439 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0836. Min Act: -0.0001

Data Index: 321902 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1639061 (Python Code)

Max Activating Token Index: 635

Text #10

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0800. Min Act: -0.0001

Data Index: 603154 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1526436 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0805. Min Act: -0.0001

Data Index: 932373 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1567533 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1365839 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1290758 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0870. Min Act: -0.0001

Data Index: 71353 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0758. Min Act: -0.0001

Data Index: 368693 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0696. Min Act: -0.0001

Data Index: 125083 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1412762 (Python Code)

Max Activating Token Index: 47