< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 5 in Layer 15

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.1015. Min Range: -3.1015

Max Act: 3.1015. Min Act: -0.1700

Data Index: 9896681 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1015. Min Range: -3.1015

Max Act: 3.0857. Min Act: -0.1700

Data Index: 2050296 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1015. Min Range: -3.1015

Max Act: 3.0384. Min Act: -0.1700

Data Index: 7185783 (The Pile)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1015. Min Range: -3.1015

Max Act: 3.0226. Min Act: -0.1700

Data Index: 8295846 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1015. Min Range: -3.1015

Max Act: 3.0226. Min Act: -0.1700

Data Index: 5362646 (The Pile)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1015. Min Range: -3.1015

Max Act: 3.0068. Min Act: -0.1700

Data Index: 8556794 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9910. Min Act: -0.1700

Data Index: 3427926 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9910. Min Act: -0.1700

Data Index: 1901004 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9751. Min Act: -0.1700

Data Index: 5230842 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9751. Min Act: -0.1700

Data Index: 1152050 (The Pile)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9593. Min Act: -0.1700

Data Index: 2469840 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9593. Min Act: -0.1700

Data Index: 6277449 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9593. Min Act: -0.1700

Data Index: 3154658 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9593. Min Act: -0.1700

Data Index: 10355733 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9593. Min Act: -0.1700

Data Index: 9460870 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9593. Min Act: -0.1700

Data Index: 8327258 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9435. Min Act: -0.1700

Data Index: 548201 (The Pile)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9435. Min Act: -0.1700

Data Index: 8142793 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9435. Min Act: -0.1700

Data Index: 5840883 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1015. Min Range: -3.1015

Max Act: 2.9435. Min Act: -0.1700

Data Index: 3430473 (The Pile)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #19