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

Dataset: The Pile

Neuron 1806 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1865843 (The Pile)

Max Activating Token Index: 727

Text #1

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1094733 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1875093 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.4791. Min Act: -0.0000

Data Index: 722629 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1075169 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.2309. Min Act: -0.0000

Data Index: 92852 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.3392. Min Act: -0.0000

Data Index: 1154092 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.5021. Min Act: -0.0000

Data Index: 422472 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.2838. Min Act: -0.0000

Data Index: 136109 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.2747. Min Act: -0.0000

Data Index: 422658 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1859155 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.2332. Min Act: -0.0000

Data Index: 998175 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.2655. Min Act: -0.0000

Data Index: 610815 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 1.8297. Min Range: -1.8297

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1692322 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1634637 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.1199. Min Act: -0.0000

Data Index: 529795 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 1.8297. Min Range: -1.8297

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1476036 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 1.8297. Min Range: -1.8297

Max Act: 0.9503. Min Act: -0.0000

Data Index: 40204 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.0508. Min Act: -0.0000

Data Index: 970287 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.0112. Min Act: -0.0000

Data Index: 142602 (The Pile)

Max Activating Token Index: 830