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

Dataset: The Pile

Neuron 2653 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: 0.2668. Min Range: -0.2668

Max Act: 0.2668. Min Act: -0.0000

Data Index: 471878 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2590. Min Act: -0.0000

Data Index: 361633 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2650. Min Act: -0.0000

Data Index: 112145 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2244. Min Act: -0.0000

Data Index: 792958 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1395877 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1642598 (The Pile)

Max Activating Token Index: 859

Text #6

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1268244 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2028. Min Act: -0.0000

Data Index: 266154 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1857728 (The Pile)

Max Activating Token Index: 924

Text #9

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1829. Min Act: -0.0000

Data Index: 980869 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1883. Min Act: -0.0000

Data Index: 534780 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1855. Min Act: -0.0000

Data Index: 691381 (The Pile)

Max Activating Token Index: 439

Text #12

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1720670 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1810. Min Act: -0.0001

Data Index: 973771 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1665. Min Act: -0.0000

Data Index: 778966 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1917. Min Act: -0.0000

Data Index: 311228 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1183347 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1685. Min Act: -0.0000

Data Index: 216000 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1058263 (The Pile)

Max Activating Token Index: 665

Text #19

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1482185 (The Pile)

Max Activating Token Index: 670