Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.8844. Min Act: -0.0000

Data Index: 1787428 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7459. Min Act: -0.0000

Data Index: 1904443 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 3.5014. Min Range: -3.5014

Max Act: 3.0489. Min Act: -0.0000

Data Index: 493346 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 3.5014. Min Range: -3.5014

Max Act: 3.1914. Min Act: -0.0000

Data Index: 442350 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.6944. Min Act: -0.0000

Data Index: 641966 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.6661. Min Act: -0.0000

Data Index: 1957414 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.8028. Min Act: -0.0000

Data Index: 258452 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7981. Min Act: -0.0000

Data Index: 392935 (The Pile)

Max Activating Token Index: 387

Text #8

Max Range: 3.5014. Min Range: -3.5014

Max Act: 3.5014. Min Act: -0.0000

Data Index: 563268 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7665. Min Act: -0.0000

Data Index: 1009997 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7053. Min Act: -0.0000

Data Index: 1282132 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.6714. Min Act: -0.0000

Data Index: 1204634 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5937. Min Act: -0.0000

Data Index: 1158463 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7857. Min Act: -0.0000

Data Index: 199900 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.4719. Min Act: -0.0000

Data Index: 361800 (The Pile)

Max Activating Token Index: 283

Text #15

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.6836. Min Act: -0.0000

Data Index: 1403972 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5717. Min Act: -0.0000

Data Index: 1641707 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5072. Min Act: -0.0000

Data Index: 283983 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7715. Min Act: -0.0000

Data Index: 1269761 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5816. Min Act: -0.0000

Data Index: 369554 (The Pile)

Max Activating Token Index: 519