< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4033 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.7883. Min Act: -0.1700

Data Index: 9412303 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.7257. Min Act: -0.1700

Data Index: 716093 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6474. Min Act: -0.1700

Data Index: 10248 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6318. Min Act: -0.1700

Data Index: 5117029 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6318. Min Act: -0.1700

Data Index: 1647758 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6318. Min Act: -0.1700

Data Index: 6112263 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6161. Min Act: -0.1700

Data Index: 3599069 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6161. Min Act: -0.1700

Data Index: 2111911 (The Pile)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6161. Min Act: -0.1700

Data Index: 10442299 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6161. Min Act: -0.1700

Data Index: 6346867 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6005. Min Act: -0.1700

Data Index: 9242137 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.6005. Min Act: -0.1700

Data Index: 1179878 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.5848. Min Act: -0.1700

Data Index: 243564 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.5848. Min Act: -0.1700

Data Index: 44184 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.5848. Min Act: -0.1700

Data Index: 6616738 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.5692. Min Act: -0.1700

Data Index: 3726180 (The Pile)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.5535. Min Act: -0.1700

Data Index: 9794649 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.5535. Min Act: -0.1700

Data Index: 7462705 (The Pile)

Max Activating Token Index: 967

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.5378. Min Act: -0.1700

Data Index: 1769985 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.5378. Min Act: -0.1700

Data Index: 653108 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #19