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

Dataset: The Pile

Neuron 3637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.8057. Min Act: -0.0000

Data Index: 1143925 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.5889. Min Act: -0.0000

Data Index: 881262 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.5600. Min Act: -0.0000

Data Index: 1851015 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.4124. Min Act: -0.0000

Data Index: 1642852 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.5265. Min Act: -0.0000

Data Index: 360451 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1712. Min Act: -0.0000

Data Index: 1138510 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1990. Min Act: -0.0000

Data Index: 1386303 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.2653. Min Act: -0.0000

Data Index: 1200890 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.0813. Min Act: -0.0000

Data Index: 1194104 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.9478. Min Act: -0.0000

Data Index: 1527403 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1902. Min Act: -0.0000

Data Index: 1260919 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.9858. Min Act: -0.0000

Data Index: 886178 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1610. Min Act: -0.0000

Data Index: 1725905 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.5933. Min Act: 0.0000

Data Index: 240747 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.2462. Min Act: -0.0000

Data Index: 1486743 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1825. Min Act: -0.0000

Data Index: 1912961 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.8827. Min Act: -0.0000

Data Index: 226233 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1511. Min Act: -0.0000

Data Index: 1105391 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.8560. Min Act: -0.0000

Data Index: 1723331 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.9651. Min Act: -0.0000

Data Index: 1994610 (The Pile)

Max Activating Token Index: 72