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

Dataset: The Pile

Neuron 133 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1414668 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1005152 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1736820 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2646. Min Act: -0.0000

Data Index: 886172 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2501. Min Act: -0.0000

Data Index: 950848 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1626863 (The Pile)

Max Activating Token Index: 310

Text #6

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1971601 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1072242 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1649934 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1917383 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1608701 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1780793 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2014. Min Act: -0.0000

Data Index: 246859 (The Pile)

Max Activating Token Index: 52

Text #13

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2079. Min Act: -0.0000

Data Index: 860127 (The Pile)

Max Activating Token Index: 82

Text #14

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1788728 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.1988. Min Act: -0.0000

Data Index: 100817 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1813250 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1673701 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1765799 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.1938. Min Act: -0.0000

Data Index: 991368 (The Pile)

Max Activating Token Index: 62