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

Dataset: The Pile

Neuron 426 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1349032 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6140. Min Act: -0.0000

Data Index: 261818 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1666829 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5592. Min Act: -0.0000

Data Index: 656446 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5708. Min Act: -0.0000

Data Index: 764859 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1618618 (The Pile)

Max Activating Token Index: 5

Text #6

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5692. Min Act: -0.0000

Data Index: 827794 (The Pile)

Max Activating Token Index: 4

Text #7

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1394901 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5740. Min Act: -0.0000

Data Index: 845909 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5715. Min Act: -0.0000

Data Index: 972949 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1771532 (The Pile)

Max Activating Token Index: 7

Text #11

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1573627 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5704. Min Act: -0.0000

Data Index: 894113 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1087673 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5686. Min Act: -0.0000

Data Index: 506437 (The Pile)

Max Activating Token Index: 4

Text #15

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5489. Min Act: -0.0000

Data Index: 982828 (The Pile)

Max Activating Token Index: 6

Text #16

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1623837 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1970758 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5438. Min Act: -0.0000

Data Index: 707453 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5586. Min Act: -0.0000

Data Index: 487789 (The Pile)

Max Activating Token Index: 15