< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1164 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7868. Min Act: -0.1700

Data Index: 2242363 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.8187. Min Act: -0.1700

Data Index: 638860 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.8187. Min Act: -0.1700

Data Index: 8514517 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7868. Min Act: -0.1700

Data Index: 5469144 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7389. Min Act: -0.1700

Data Index: 7058057 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7389. Min Act: -0.1700

Data Index: 6137699 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7709. Min Act: -0.1700

Data Index: 7934078 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7389. Min Act: -0.1700

Data Index: 7578200 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7230. Min Act: -0.1700

Data Index: 2325730 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7389. Min Act: -0.1700

Data Index: 8697458 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7389. Min Act: -0.1700

Data Index: 10671349 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7230. Min Act: -0.1700

Data Index: 1707113 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7070. Min Act: -0.1700

Data Index: 1709096 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.6910. Min Act: -0.1700

Data Index: 2962783 (The Pile)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7070. Min Act: -0.1700

Data Index: 1496600 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7070. Min Act: -0.1700

Data Index: 4682647 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.6910. Min Act: -0.1700

Data Index: 4724937 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.7070. Min Act: -0.1700

Data Index: 3095178 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.6589. Min Act: -0.1700

Data Index: 6838486 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8187. Min Range: -2.8187

Max Act: 2.6750. Min Act: -0.1700

Data Index: 4942624 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #19