< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 39 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.7049. Min Act: -0.1700

Data Index: 7937986 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6736. Min Act: -0.1700

Data Index: 6257632 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6579. Min Act: -0.1700

Data Index: 4082722 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6579. Min Act: -0.1700

Data Index: 8996883 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6579. Min Act: -0.1700

Data Index: 1668462 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6579. Min Act: -0.1700

Data Index: 319886 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6423. Min Act: -0.1700

Data Index: 4933406 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6423. Min Act: -0.1700

Data Index: 9096997 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6423. Min Act: -0.1700

Data Index: 8775917 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6266. Min Act: -0.1700

Data Index: 3963290 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6266. Min Act: -0.1700

Data Index: 6183841 (The Pile)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6266. Min Act: -0.1700

Data Index: 1765990 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6266. Min Act: -0.1700

Data Index: 1372665 (The Pile)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6266. Min Act: -0.1700

Data Index: 2069418 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6110. Min Act: -0.1700

Data Index: 3125201 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6110. Min Act: -0.1700

Data Index: 1144083 (The Pile)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6110. Min Act: -0.1700

Data Index: 5705863 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6110. Min Act: -0.1700

Data Index: 6255154 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6110. Min Act: -0.1700

Data Index: 468871 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7049. Min Range: -3.7049

Max Act: 3.6110. Min Act: -0.1700

Data Index: 146222 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #19