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

Dataset: The Pile

Neuron 5022 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: 3.0898. Min Range: -3.0898

Max Act: 3.0898. Min Act: -0.0000

Data Index: 6787 (The Pile)

Max Activating Token Index: 883

Text #1

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.5065. Min Act: -0.0000

Data Index: 460477 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.4833. Min Act: -0.0000

Data Index: 1290774 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.3119. Min Act: -0.0000

Data Index: 574427 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.6108. Min Act: -0.0000

Data Index: 1605839 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.1753. Min Act: -0.0000

Data Index: 1047146 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.9291. Min Act: -0.0000

Data Index: 1440992 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.2369. Min Act: -0.0000

Data Index: 1108745 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.8328. Min Act: -0.0000

Data Index: 1517001 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.9078. Min Act: -0.0000

Data Index: 1164013 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.2240. Min Act: -0.0000

Data Index: 1076390 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.2116. Min Act: -0.0000

Data Index: 1493009 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.0601. Min Act: -0.0000

Data Index: 306777 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.7363. Min Act: -0.0000

Data Index: 1103375 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.8111. Min Act: -0.0000

Data Index: 213402 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.8219. Min Act: -0.0000

Data Index: 896937 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.7998. Min Act: -0.0000

Data Index: 1761491 (The Pile)

Max Activating Token Index: 434

Text #17

Max Range: 3.0898. Min Range: -3.0898

Max Act: 2.0191. Min Act: -0.0000

Data Index: 1703470 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.7998. Min Act: -0.0000

Data Index: 574884 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 3.0898. Min Range: -3.0898

Max Act: 1.7963. Min Act: -0.0000

Data Index: 156686 (The Pile)

Max Activating Token Index: 285