< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 56 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: 6.9067. Min Range: -6.9067

Max Act: 6.9067. Min Act: -0.1700

Data Index: 5872223 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.8754. Min Act: -0.1700

Data Index: 10572000 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.8442. Min Act: -0.1700

Data Index: 10753845 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.8754. Min Act: -0.1700

Data Index: 3160192 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.6879. Min Act: -0.1700

Data Index: 10274176 (The Pile)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.7192. Min Act: -0.1700

Data Index: 6373565 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.6567. Min Act: -0.1700

Data Index: 3690246 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.6254. Min Act: -0.1700

Data Index: 8132806 (The Pile)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.5942. Min Act: -0.1700

Data Index: 2271480 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.5942. Min Act: -0.1700

Data Index: 8559496 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.5629. Min Act: -0.1700

Data Index: 7576327 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.4692. Min Act: -0.1700

Data Index: 1192909 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.3754. Min Act: -0.1700

Data Index: 9189269 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.2504. Min Act: -0.1700

Data Index: 5356032 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.2192. Min Act: -0.1700

Data Index: 4628445 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.1567. Min Act: -0.1700

Data Index: 7958890 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.1567. Min Act: -0.1700

Data Index: 4626503 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.1254. Min Act: -0.1700

Data Index: 2135688 (The Pile)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.1567. Min Act: -0.1700

Data Index: 9104634 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.9067. Min Range: -6.9067

Max Act: 6.1254. Min Act: -0.1700

Data Index: 9960668 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #19