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

Dataset: The Pile

Neuron 134 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.8788. Min Act: -0.0000

Data Index: 864772 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.6806. Min Act: -0.0000

Data Index: 1402357 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.6515. Min Act: -0.0001

Data Index: 1841387 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.5004. Min Act: -0.0000

Data Index: 781287 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.7830. Min Act: -0.0000

Data Index: 57089 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.5636. Min Act: -0.0000

Data Index: 189617 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.3981. Min Act: -0.0000

Data Index: 727354 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.5040. Min Act: -0.0000

Data Index: 776917 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.2806. Min Act: -0.0001

Data Index: 525644 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.3059. Min Act: -0.0000

Data Index: 928576 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.2887. Min Act: -0.0000

Data Index: 1152522 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.0966. Min Act: -0.0000

Data Index: 1617196 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.2220. Min Act: -0.0000

Data Index: 1056740 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.2086. Min Act: -0.0000

Data Index: 767004 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.1771. Min Act: -0.0000

Data Index: 1105543 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.2436. Min Act: -0.0000

Data Index: 682369 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.2631. Min Act: -0.0001

Data Index: 1186826 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.1218. Min Act: -0.0000

Data Index: 1563313 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.0976. Min Act: -0.0000

Data Index: 1959610 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 3.8788. Min Range: -3.8788

Max Act: 3.0701. Min Act: -0.0000

Data Index: 746376 (The Pile)

Max Activating Token Index: 31