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

Dataset: The Pile

Neuron 3945 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.6738. Min Act: -0.0000

Data Index: 904636 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.4671. Min Act: -0.0000

Data Index: 785225 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.4757. Min Act: -0.0000

Data Index: 596284 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.4381. Min Act: -0.0000

Data Index: 734345 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3724. Min Act: -0.0000

Data Index: 895946 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3984. Min Act: -0.0000

Data Index: 173671 (The Pile)

Max Activating Token Index: 37

Text #6

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3498. Min Act: -0.0000

Data Index: 1073783 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3056. Min Act: -0.0000

Data Index: 784393 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1121438 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3817. Min Act: -0.0000

Data Index: 348299 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3013. Min Act: -0.0000

Data Index: 228273 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3591. Min Act: -0.0000

Data Index: 1263031 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.2045. Min Act: -0.0000

Data Index: 334072 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3124. Min Act: -0.0000

Data Index: 659515 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.2847. Min Act: -0.0000

Data Index: 340317 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.2863. Min Act: -0.0000

Data Index: 1171935 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1926506 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1037528 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1901. Min Act: -0.0000

Data Index: 828620 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1873. Min Act: -0.0000

Data Index: 101200 (The Pile)

Max Activating Token Index: 137