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

Dataset: The Pile

Neuron 3558 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: 1.2836. Min Range: -1.2836

Max Act: 1.2836. Min Act: -0.0000

Data Index: 125259 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.1767. Min Act: -0.0000

Data Index: 1144158 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0848. Min Act: -0.0000

Data Index: 444579 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0261. Min Act: -0.0000

Data Index: 927087 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1509624 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1240730 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1840756 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1551134 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1590766 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1309496 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0000. Min Act: -0.0000

Data Index: 626763 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1173849 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9846. Min Act: -0.0000

Data Index: 240032 (The Pile)

Max Activating Token Index: 271

Text #13

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1008879 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1732209 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9788. Min Act: -0.0000

Data Index: 353396 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1607710 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1369700 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9354. Min Act: -0.0000

Data Index: 842237 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9162. Min Act: -0.0000

Data Index: 820663 (The Pile)

Max Activating Token Index: 140