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

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

Neuron 5106 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9697. Min Act: -0.0000

Data Index: 938474 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8093. Min Act: -0.0000

Data Index: 192625 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5736. Min Act: -0.0000

Data Index: 783419 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1333744 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5975. Min Act: -0.0000

Data Index: 901523 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1044391 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5389. Min Act: -0.0000

Data Index: 934558 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5056. Min Act: -0.0000

Data Index: 356776 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1361826 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1048881 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5100. Min Act: -0.0000

Data Index: 27889 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1038813 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4911. Min Act: -0.0000

Data Index: 738313 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4895. Min Act: -0.0000

Data Index: 397043 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1420685 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1339858 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1310854 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1353041 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1547598 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4848. Min Act: -0.0000

Data Index: 282258 (C4 (Web Text))

Max Activating Token Index: 500