Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3210 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: 0.0005

Data Index: 1468405 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0941. Min Act: 0.0002

Data Index: 1156900 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0893. Min Act: 0.0007

Data Index: 936034 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0746. Min Act: 0.0002

Data Index: 1840005 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0741. Min Act: 0.0003

Data Index: 1097325 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0741. Min Act: 0.0003

Data Index: 480080 (The Pile)

Max Activating Token Index: 3

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0735. Min Act: 0.0001

Data Index: 1301048 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0702. Min Act: -0.0000

Data Index: 95 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0713. Min Act: 0.0005

Data Index: 1987397 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0686. Min Act: 0.0001

Data Index: 805706 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0706. Min Act: 0.0002

Data Index: 3001 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0673. Min Act: 0.0004

Data Index: 1088717 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0672. Min Act: 0.0002

Data Index: 1130381 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0662. Min Act: 0.0002

Data Index: 896853 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0663. Min Act: 0.0000

Data Index: 177867 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0663. Min Act: 0.0005

Data Index: 1889480 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0656. Min Act: 0.0005

Data Index: 1226197 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0653. Min Act: 0.0005

Data Index: 872068 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0644. Min Act: 0.0003

Data Index: 309607 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0642. Min Act: 0.0003

Data Index: 729692 (The Pile)

Max Activating Token Index: 67