< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1 in Layer 12

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2216. Min Range: -3.2216

Max Act: 3.2216. Min Act: -0.1700

Data Index: 7145770 (The Pile)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2216. Min Range: -3.2216

Max Act: 3.0956. Min Act: -0.1700

Data Index: 1514644 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2216. Min Range: -3.2216

Max Act: 3.0956. Min Act: -0.1700

Data Index: 6023377 (The Pile)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2216. Min Range: -3.2216

Max Act: 3.0167. Min Act: -0.1700

Data Index: 2948803 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2216. Min Range: -3.2216

Max Act: 3.0009. Min Act: -0.1700

Data Index: 6271227 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2216. Min Range: -3.2216

Max Act: 3.0009. Min Act: -0.1700

Data Index: 5550972 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2216. Min Range: -3.2216

Max Act: 3.0009. Min Act: -0.1700

Data Index: 1272417 (The Pile)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2216. Min Range: -3.2216

Max Act: 3.0009. Min Act: -0.1700

Data Index: 9583087 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.9693. Min Act: -0.1700

Data Index: 6102 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.9534. Min Act: -0.1700

Data Index: 9875658 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.9218. Min Act: -0.1700

Data Index: 2748006 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.9218. Min Act: -0.1700

Data Index: 5577643 (The Pile)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.9218. Min Act: -0.1700

Data Index: 5632665 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.9059. Min Act: -0.1700

Data Index: 3923987 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.9059. Min Act: -0.1700

Data Index: 3144888 (The Pile)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.8900. Min Act: -0.1700

Data Index: 2361607 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.8900. Min Act: -0.1700

Data Index: 338033 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.8900. Min Act: -0.1700

Data Index: 4320509 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.8900. Min Act: -0.1700

Data Index: 4450513 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2216. Min Range: -3.2216

Max Act: 2.8900. Min Act: -0.1700

Data Index: 6690077 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #19