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

Dataset: The Pile

Neuron 3442 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: 0.8975. Min Range: -0.8975

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1946738 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1561642 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8803. Min Act: -0.0000

Data Index: 774165 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1032294 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1284254 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1119815 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1229242 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1206312 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1887886 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1833182 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6727. Min Act: -0.0000

Data Index: 720610 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1073733 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1881828 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7274. Min Act: -0.0000

Data Index: 188622 (The Pile)

Max Activating Token Index: 517

Text #14

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7047. Min Act: -0.0000

Data Index: 231017 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1122491 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1000781 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1600716 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1359617 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1025530 (The Pile)

Max Activating Token Index: 175