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

Dataset: The Pile

Neuron 3379 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: 0.2800. Min Range: -0.2800

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1028151 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2480. Min Act: -0.0000

Data Index: 444807 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2488. Min Act: -0.0000

Data Index: 472909 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2201. Min Act: -0.0000

Data Index: 376043 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2068. Min Act: -0.0000

Data Index: 720905 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1835362 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2009. Min Act: -0.0000

Data Index: 909090 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1938. Min Act: -0.0000

Data Index: 542684 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2004. Min Act: -0.0000

Data Index: 484031 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1826. Min Act: -0.0000

Data Index: 950365 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1420577 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1033700 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1863834 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1244453 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1349060 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1808746 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1839. Min Act: -0.0000

Data Index: 233420 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1592. Min Act: -0.0000

Data Index: 107270 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1595695 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.1859. Min Act: -0.0000

Data Index: 742453 (The Pile)

Max Activating Token Index: 542