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

Dataset: The Pile

Neuron 647 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: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 885492 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 942791 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 238685 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 69397 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 719426 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1763423 (The Pile)

Max Activating Token Index: 2

Text #6

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1228953 (The Pile)

Max Activating Token Index: 2

Text #7

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1667064 (The Pile)

Max Activating Token Index: 3

Text #8

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 825594 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1704787 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 215763 (The Pile)

Max Activating Token Index: 960

Text #11

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1383083 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 475476 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1796020 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 651890 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 886692 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1800675 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1168028 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 433539 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1718118 (The Pile)

Max Activating Token Index: 1