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

Dataset: The Pile

Neuron 1810 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1061096 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 499614 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 305428 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1099131 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1898087 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1417872 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1044147 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 28458 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1019126 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1391182 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 448496 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1976112 (The Pile)

Max Activating Token Index: 873

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1104422 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1496655 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1425654 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 771801 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1918219 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1302308 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1380176 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 855927 (The Pile)

Max Activating Token Index: 711