< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 25 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.1740. Min Act: -0.1700

Data Index: 8258190 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.1740. Min Act: -0.1700

Data Index: 9131253 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.1425. Min Act: -0.1700

Data Index: 5520484 (The Pile)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.1268. Min Act: -0.1700

Data Index: 9940462 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.1268. Min Act: -0.1700

Data Index: 9125683 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.1110. Min Act: -0.1700

Data Index: 5199706 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0952. Min Act: -0.1700

Data Index: 3388076 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0952. Min Act: -0.1700

Data Index: 7253964 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0952. Min Act: -0.1700

Data Index: 2278257 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0795. Min Act: -0.1700

Data Index: 8906590 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0637. Min Act: -0.1700

Data Index: 9893010 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0637. Min Act: -0.1700

Data Index: 7266818 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0637. Min Act: -0.1700

Data Index: 7338482 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0637. Min Act: -0.1700

Data Index: 4076529 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0479. Min Act: -0.1700

Data Index: 101405 (The Pile)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0479. Min Act: -0.1700

Data Index: 9333876 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0479. Min Act: -0.1700

Data Index: 24261 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0479. Min Act: -0.1700

Data Index: 4016559 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0479. Min Act: -0.1700

Data Index: 6497506 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1740. Min Range: -3.1740

Max Act: 3.0479. Min Act: -0.1700

Data Index: 1044338 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #19