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

Dataset: The Pile

Neuron 3941 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 1456591 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 456015 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 1275247 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 1645156 (The Pile)

Max Activating Token Index: 459

Text #4

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 1512194 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 1099375 (The Pile)

Max Activating Token Index: 494

Text #6

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 1249495 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 1733873 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1405902 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0000

Data Index: 1724511 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1415596 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1274725 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 117340 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1535428 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1403033 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1685140 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 624453 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1452702 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1162611 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1575629 (The Pile)

Max Activating Token Index: 511