< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 49 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: 3.0612. Min Range: -3.0612

Max Act: 3.0612. Min Act: -0.1700

Data Index: 8441455 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0612. Min Act: -0.1700

Data Index: 452953 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0455. Min Act: -0.1700

Data Index: 3669135 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0297. Min Act: -0.1700

Data Index: 2005725 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0297. Min Act: -0.1700

Data Index: 7944741 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0297. Min Act: -0.1700

Data Index: 2186039 (The Pile)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0297. Min Act: -0.1700

Data Index: 8846523 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0139. Min Act: -0.1700

Data Index: 7923734 (The Pile)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0139. Min Act: -0.1700

Data Index: 8308412 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0139. Min Act: -0.1700

Data Index: 8938304 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0139. Min Act: -0.1700

Data Index: 1512818 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9981. Min Act: -0.1700

Data Index: 520420 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9981. Min Act: -0.1700

Data Index: 10120027 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9981. Min Act: -0.1700

Data Index: 8908033 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9981. Min Act: -0.1700

Data Index: 8602568 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9981. Min Act: -0.1700

Data Index: 42280 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9981. Min Act: -0.1700

Data Index: 9418241 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9822. Min Act: -0.1700

Data Index: 575767 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9822. Min Act: -0.1700

Data Index: 8096665 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9822. Min Act: -0.1700

Data Index: 9085627 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #19