< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 32 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: 3.9435. Min Range: -3.9435

Max Act: 3.9435. Min Act: -0.1700

Data Index: 5250792 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.9122. Min Act: -0.1700

Data Index: 3298285 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.8810. Min Act: -0.1700

Data Index: 10063190 (The Pile)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.8340. Min Act: -0.1700

Data Index: 2997088 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.8028. Min Act: -0.1700

Data Index: 1384474 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.8028. Min Act: -0.1700

Data Index: 5066502 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1570832 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7715. Min Act: -0.1700

Data Index: 10609422 (The Pile)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7558. Min Act: -0.1700

Data Index: 6299192 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7558. Min Act: -0.1700

Data Index: 9586432 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7402. Min Act: -0.1700

Data Index: 2072750 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7402. Min Act: -0.1700

Data Index: 1808720 (The Pile)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7245. Min Act: -0.1700

Data Index: 8080592 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7245. Min Act: -0.1700

Data Index: 1761949 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7089. Min Act: -0.1700

Data Index: 8641946 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7089. Min Act: -0.1700

Data Index: 4370445 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7089. Min Act: -0.1700

Data Index: 10710582 (The Pile)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6932. Min Act: -0.1700

Data Index: 5160851 (The Pile)

Max Activating Token Index: 461

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6932. Min Act: -0.1700

Data Index: 10164386 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6932. Min Act: -0.1700

Data Index: 8216279 (The Pile)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #19