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

Dataset: The Pile

Neuron 4066 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3828. Min Act: -0.0000

Data Index: 672066 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1318554 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1466880 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2831. Min Act: -0.0000

Data Index: 761192 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2159. Min Act: -0.0000

Data Index: 173014 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2482. Min Act: -0.0000

Data Index: 755288 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2278. Min Act: -0.0000

Data Index: 625253 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1259163 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2016. Min Act: -0.0000

Data Index: 533675 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2089. Min Act: -0.0000

Data Index: 823441 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1836773 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2125. Min Act: -0.0000

Data Index: 146013 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1809. Min Act: -0.0000

Data Index: 192873 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1689. Min Act: -0.0000

Data Index: 735135 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1851. Min Act: -0.0000

Data Index: 636595 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1760. Min Act: -0.0000

Data Index: 85961 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1483251 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1285. Min Act: -0.0000

Data Index: 270063 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1526116 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1217613 (The Pile)

Max Activating Token Index: 194