Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1736799 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.3053. Min Act: -0.0000

Data Index: 592159 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1925130 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2243. Min Act: -0.0000

Data Index: 920352 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1760327 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1522463 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2128. Min Act: -0.0000

Data Index: 371177 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2152. Min Act: -0.0000

Data Index: 546612 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2082. Min Act: -0.0000

Data Index: 369077 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1524258 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1095806 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2118. Min Act: -0.0000

Data Index: 489198 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1979560 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.1927. Min Act: -0.0000

Data Index: 323188 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1334202 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.1766. Min Act: -0.0000

Data Index: 979901 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.1734. Min Act: -0.0000

Data Index: 48372 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1356442 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.1902. Min Act: -0.0000

Data Index: 50534 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1900082 (The Pile)

Max Activating Token Index: 639