< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1917 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5000. Min Act: -0.1700

Data Index: 9557377 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5313. Min Act: -0.1700

Data Index: 540030 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.4530. Min Act: -0.1700

Data Index: 3454716 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5156. Min Act: -0.1700

Data Index: 2631046 (The Pile)

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5626. Min Act: -0.1700

Data Index: 6101036 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5000. Min Act: -0.1700

Data Index: 6904030 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5156. Min Act: -0.1700

Data Index: 9138209 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.4843. Min Act: -0.1700

Data Index: 8448853 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5626. Min Act: -0.1700

Data Index: 7809009 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.3588. Min Act: -0.1700

Data Index: 7258448 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5626. Min Act: -0.1700

Data Index: 1473917 (The Pile)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5313. Min Act: -0.1700

Data Index: 1490947 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.4216. Min Act: -0.1700

Data Index: 3037360 (The Pile)

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.4843. Min Act: -0.1700

Data Index: 5030333 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5000. Min Act: -0.1700

Data Index: 882841 (The Pile)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.4216. Min Act: -0.1700

Data Index: 2939975 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5313. Min Act: -0.1700

Data Index: 5817961 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5470. Min Act: -0.1700

Data Index: 10085513 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.4530. Min Act: -0.1700

Data Index: 5697817 (The Pile)

Max Activating Token Index: 838

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5783. Min Range: -3.5783

Max Act: 3.5783. Min Act: -0.1700

Data Index: 159278 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #19