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

Dataset: The Pile

Neuron 5109 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.6922. Min Act: -0.0000

Data Index: 113507 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.8456. Min Act: -0.0000

Data Index: 1786260 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.6609. Min Act: -0.0000

Data Index: 698114 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.7062. Min Act: -0.0000

Data Index: 825580 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5122. Min Act: -0.0000

Data Index: 759575 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5777. Min Act: -0.0000

Data Index: 182893 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4621. Min Act: -0.0000

Data Index: 783112 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.6006. Min Act: -0.0000

Data Index: 595651 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5139. Min Act: -0.0000

Data Index: 426618 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5010. Min Act: -0.0000

Data Index: 285127 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1188862 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4719. Min Act: -0.0000

Data Index: 1928181 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5353. Min Act: -0.0000

Data Index: 1443197 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1931856 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1897826 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1506267 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1069700 (The Pile)

Max Activating Token Index: 795

Text #17

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1549967 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2698. Min Act: -0.0000

Data Index: 1832619 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.3271. Min Act: -0.0000

Data Index: 415756 (The Pile)

Max Activating Token Index: 456