< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 25 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.6836. Min Act: -0.1700

Data Index: 2033138 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.6515. Min Act: -0.1700

Data Index: 10036021 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.6194. Min Act: -0.1700

Data Index: 2070295 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.6194. Min Act: -0.1700

Data Index: 4950668 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5872. Min Act: -0.1700

Data Index: 531640 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5711. Min Act: -0.1700

Data Index: 5191570 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5872. Min Act: -0.1700

Data Index: 7948067 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5550. Min Act: -0.1700

Data Index: 2032346 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5711. Min Act: -0.1700

Data Index: 6483676 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5711. Min Act: -0.1700

Data Index: 278853 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5550. Min Act: -0.1700

Data Index: 7879958 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5388. Min Act: -0.1700

Data Index: 9743793 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5550. Min Act: -0.1700

Data Index: 8779466 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5550. Min Act: -0.1700

Data Index: 5614915 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5550. Min Act: -0.1700

Data Index: 2673392 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5388. Min Act: -0.1700

Data Index: 6468261 (The Pile)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5550. Min Act: -0.1700

Data Index: 980896 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5388. Min Act: -0.1700

Data Index: 8861750 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5227. Min Act: -0.1700

Data Index: 6704531 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6836. Min Range: -2.6836

Max Act: 2.5227. Min Act: -0.1700

Data Index: 2317098 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #19