< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.8603. Min Act: -0.1700

Data Index: 1640635 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.7666. Min Act: -0.1700

Data Index: 7563912 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.7353. Min Act: -0.1700

Data Index: 5882601 (The Pile)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.7041. Min Act: -0.1700

Data Index: 7823769 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.6728. Min Act: -0.1700

Data Index: 9623920 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.6728. Min Act: -0.1700

Data Index: 8329489 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.6728. Min Act: -0.1700

Data Index: 2046036 (The Pile)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.6728. Min Act: -0.1700

Data Index: 3163244 (The Pile)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.6416. Min Act: -0.1700

Data Index: 3672972 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.6416. Min Act: -0.1700

Data Index: 465459 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.6103. Min Act: -0.1700

Data Index: 4117387 (The Pile)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.6103. Min Act: -0.1700

Data Index: 5160256 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.5791. Min Act: -0.1700

Data Index: 2254252 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.5791. Min Act: -0.1700

Data Index: 3516817 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.5791. Min Act: -0.1700

Data Index: 3533907 (The Pile)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.5791. Min Act: -0.1700

Data Index: 8546289 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.5791. Min Act: -0.1700

Data Index: 3074865 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.5791. Min Act: -0.1700

Data Index: 5149131 (The Pile)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.5791. Min Act: -0.1700

Data Index: 8187696 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.8603. Min Range: -7.8603

Max Act: 7.5791. Min Act: -0.1700

Data Index: 1103569 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #19