< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2036 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: 2.7088. Min Range: -2.7088

Max Act: 2.7088. Min Act: -0.1700

Data Index: 2818734 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.6768. Min Act: -0.1700

Data Index: 2811183 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.6448. Min Act: -0.1700

Data Index: 9475609 (The Pile)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.6608. Min Act: -0.1700

Data Index: 1787411 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.6608. Min Act: -0.1700

Data Index: 4940468 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.6448. Min Act: -0.1700

Data Index: 4974748 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.6126. Min Act: -0.1700

Data Index: 2840638 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.6287. Min Act: -0.1700

Data Index: 8452712 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5965. Min Act: -0.1700

Data Index: 7721656 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5965. Min Act: -0.1700

Data Index: 2008982 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5965. Min Act: -0.1700

Data Index: 2919331 (The Pile)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5965. Min Act: -0.1700

Data Index: 6133719 (The Pile)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5643. Min Act: -0.1700

Data Index: 4767969 (The Pile)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5965. Min Act: -0.1700

Data Index: 10178834 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5804. Min Act: -0.1700

Data Index: 7509986 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5804. Min Act: -0.1700

Data Index: 10561964 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5804. Min Act: -0.1700

Data Index: 2354228 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5804. Min Act: -0.1700

Data Index: 5584003 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5804. Min Act: -0.1700

Data Index: 9320569 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.7088. Min Range: -2.7088

Max Act: 2.5643. Min Act: -0.1700

Data Index: 8675268 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #19