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

Dataset: The Pile

Neuron 0 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: 0.2836. Min Range: -0.2836

Max Act: 0.2836. Min Act: -0.0000

Data Index: 494159 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2268. Min Act: -0.0000

Data Index: 85139 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2115. Min Act: -0.0000

Data Index: 552879 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1277266 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1537874 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1253585 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1751. Min Act: -0.0000

Data Index: 704067 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1296860 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1732491 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1632252 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1289394 (The Pile)

Max Activating Token Index: 717

Text #11

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1604. Min Act: -0.0000

Data Index: 989784 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1414164 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1836. Min Act: -0.0000

Data Index: 940439 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1452. Min Act: -0.0000

Data Index: 113485 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1490021 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1479251 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1117332 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1475. Min Act: -0.0000

Data Index: 37639 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1623880 (The Pile)

Max Activating Token Index: 386