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

Dataset: The Pile

Neuron 502 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: 1.2839. Min Range: -1.2839

Max Act: 1.2218. Min Act: -0.0000

Data Index: 811122 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1040744 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1704. Min Act: -0.0000

Data Index: 479820 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1564608 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1741861 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1202841 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1354783 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1270523 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1027. Min Act: -0.0000

Data Index: 89827 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0849. Min Act: -0.0000

Data Index: 1031625 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2141. Min Act: -0.0000

Data Index: 18868 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1106. Min Act: -0.0000

Data Index: 305395 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0927. Min Act: -0.0000

Data Index: 578049 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1568985 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1231068 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1418216 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9613. Min Act: -0.0000

Data Index: 334735 (The Pile)

Max Activating Token Index: 844

Text #17

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1025166 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0585. Min Act: -0.0000

Data Index: 69473 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1258382 (The Pile)

Max Activating Token Index: 473