Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 123 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1278948 (The Pile)

Max Activating Token Index: 886

Text #1

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1450863 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1538819 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1793. Min Act: -0.0000

Data Index: 866219 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1775. Min Act: -0.0000

Data Index: 674787 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1514626 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1750. Min Act: -0.0000

Data Index: 250555 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1798. Min Act: -0.0001

Data Index: 344922 (The Pile)

Max Activating Token Index: 868

Text #8

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1672. Min Act: -0.0000

Data Index: 523639 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1546. Min Act: -0.0000

Data Index: 410815 (The Pile)

Max Activating Token Index: 804

Text #10

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1233463 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1637. Min Act: -0.0000

Data Index: 463239 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1247220 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1644. Min Act: -0.0000

Data Index: 71053 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1950460 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1372298 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1460. Min Act: -0.0001

Data Index: 107920 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1064637 (The Pile)

Max Activating Token Index: 289

Text #18

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1901088 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1212307 (The Pile)

Max Activating Token Index: 618