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

Dataset: The Pile

Neuron 1201 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: 0.1003. Min Range: -0.1003

Max Act: 0.1003. Min Act: 0.0000

Data Index: 964666 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0943. Min Act: -0.0000

Data Index: 670434 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0803. Min Act: 0.0000

Data Index: 869301 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1201430 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0779. Min Act: -0.0000

Data Index: 469186 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1060906 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0687. Min Act: 0.0000

Data Index: 1041017 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0669. Min Act: 0.0000

Data Index: 1730437 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0662. Min Act: -0.0000

Data Index: 487205 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0659. Min Act: 0.0000

Data Index: 1148441 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1286628 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1018497 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1394844 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0642. Min Act: 0.0000

Data Index: 927439 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0639. Min Act: -0.0000

Data Index: 513738 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0637. Min Act: 0.0000

Data Index: 827012 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1687889 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0637. Min Act: -0.0000

Data Index: 921241 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0634. Min Act: 0.0000

Data Index: 1105903 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1571140 (The Pile)

Max Activating Token Index: 112