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

Dataset: The Pile

Neuron 862 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: 0.2236. Min Range: -0.2236

Max Act: 0.2091. Min Act: -0.0000

Data Index: 107011 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1052584 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1855933 (The Pile)

Max Activating Token Index: 924

Text #3

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1038504 (The Pile)

Max Activating Token Index: 689

Text #4

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1881675 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1913173 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1928. Min Act: -0.0000

Data Index: 863802 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1706. Min Act: -0.0000

Data Index: 901173 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1826. Min Act: -0.0000

Data Index: 598382 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1853. Min Act: -0.0000

Data Index: 347064 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1240003 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1198583 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1170345 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1680822 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1800792 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1847. Min Act: -0.0000

Data Index: 427948 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1565. Min Act: -0.0000

Data Index: 688785 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1733. Min Act: -0.0000

Data Index: 2461 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1389502 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1609. Min Act: -0.0000

Data Index: 467617 (The Pile)

Max Activating Token Index: 774