< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2996 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.7930. Min Act: -0.1700

Data Index: 8539480 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.6209. Min Act: -0.1700

Data Index: 1964396 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.5739. Min Act: -0.1700

Data Index: 2288624 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.5269. Min Act: -0.1700

Data Index: 9721997 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.5113. Min Act: -0.1700

Data Index: 10211504 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.5113. Min Act: -0.1700

Data Index: 9311547 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.5113. Min Act: -0.1700

Data Index: 3010456 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.5113. Min Act: -0.1700

Data Index: 6004700 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.5113. Min Act: -0.1700

Data Index: 8841025 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.5113. Min Act: -0.1700

Data Index: 8296646 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4799. Min Act: -0.1700

Data Index: 732749 (The Pile)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4799. Min Act: -0.1700

Data Index: 8741615 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4799. Min Act: -0.1700

Data Index: 2740900 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4643. Min Act: -0.1700

Data Index: 8942461 (The Pile)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4643. Min Act: -0.1700

Data Index: 6561167 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4486. Min Act: -0.1700

Data Index: 7329594 (The Pile)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4486. Min Act: -0.1700

Data Index: 5460299 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4486. Min Act: -0.1700

Data Index: 3537796 (The Pile)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4329. Min Act: -0.1700

Data Index: 8213242 (The Pile)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7930. Min Range: -3.7930

Max Act: 3.4329. Min Act: -0.1700

Data Index: 3185647 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #19