< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 14 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.9837. Min Act: -0.1700

Data Index: 1454266 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.8728. Min Act: -0.1700

Data Index: 8244887 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.8569. Min Act: -0.1700

Data Index: 2011455 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.8569. Min Act: -0.1700

Data Index: 5959207 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.8410. Min Act: -0.1700

Data Index: 7755964 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.8410. Min Act: -0.1700

Data Index: 642062 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.8251. Min Act: -0.1700

Data Index: 6562882 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.8092. Min Act: -0.1700

Data Index: 10554185 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.8092. Min Act: -0.1700

Data Index: 5326755 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7933. Min Act: -0.1700

Data Index: 5940542 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7773. Min Act: -0.1700

Data Index: 8920799 (The Pile)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7773. Min Act: -0.1700

Data Index: 1474617 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7614. Min Act: -0.1700

Data Index: 5476564 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7614. Min Act: -0.1700

Data Index: 8452536 (The Pile)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7614. Min Act: -0.1700

Data Index: 9930627 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7454. Min Act: -0.1700

Data Index: 4018158 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7454. Min Act: -0.1700

Data Index: 5528209 (The Pile)

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7454. Min Act: -0.1700

Data Index: 8989324 (The Pile)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7454. Min Act: -0.1700

Data Index: 5245733 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9837. Min Range: -2.9837

Max Act: 2.7454. Min Act: -0.1700

Data Index: 5018637 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #19