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

Dataset: The Pile

Neuron 1890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1739370 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6829. Min Act: -0.0000

Data Index: 194423 (The Pile)

Max Activating Token Index: 659

Text #2

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1854775 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6861. Min Act: -0.0000

Data Index: 296258 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1232859 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1980155 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6587. Min Act: -0.0001

Data Index: 795936 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6372. Min Act: -0.0000

Data Index: 842963 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5954. Min Act: -0.0000

Data Index: 424514 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1990079 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6404. Min Act: -0.0000

Data Index: 230891 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6212. Min Act: -0.0000

Data Index: 726773 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6325. Min Act: -0.0001

Data Index: 561247 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6237. Min Act: -0.0000

Data Index: 387275 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6051. Min Act: -0.0000

Data Index: 232531 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1283950 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1438472 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6581. Min Act: -0.0001

Data Index: 277386 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6058. Min Act: -0.0000

Data Index: 817033 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6056. Min Act: -0.0000

Data Index: 784486 (The Pile)

Max Activating Token Index: 252