Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3902 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.7924. Min Act: -0.0000

Data Index: 222014 (The Pile)

Max Activating Token Index: 27

Text #1

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1858488 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6720. Min Act: -0.0000

Data Index: 502077 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1495104 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6115. Min Act: -0.0000

Data Index: 834102 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1892133 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6015. Min Act: -0.0000

Data Index: 729103 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5932. Min Act: -0.0000

Data Index: 239620 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1022058 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1279456 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1519364 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5285. Min Act: -0.0000

Data Index: 767403 (The Pile)

Max Activating Token Index: 321

Text #12

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1966722 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6694. Min Act: -0.0000

Data Index: 242615 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5052. Min Act: -0.0000

Data Index: 944855 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1414038 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1462730 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1064820 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1294267 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1382297 (The Pile)

Max Activating Token Index: 967