< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4088 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.2014. Min Act: -0.1700

Data Index: 8444356 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1699. Min Act: -0.1700

Data Index: 4262873 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1384. Min Act: -0.1700

Data Index: 10296576 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1227. Min Act: -0.1700

Data Index: 7592364 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1227. Min Act: -0.1700

Data Index: 3924117 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1227. Min Act: -0.1700

Data Index: 10002107 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1069. Min Act: -0.1700

Data Index: 9748663 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1069. Min Act: -0.1700

Data Index: 297615 (The Pile)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1069. Min Act: -0.1700

Data Index: 5759937 (The Pile)

Max Activating Token Index: 797

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1069. Min Act: -0.1700

Data Index: 2053664 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1069. Min Act: -0.1700

Data Index: 7762837 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1069. Min Act: -0.1700

Data Index: 7616649 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.1069. Min Act: -0.1700

Data Index: 1758053 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.0912. Min Act: -0.1700

Data Index: 5100652 (The Pile)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.0912. Min Act: -0.1700

Data Index: 6678277 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.0912. Min Act: -0.1700

Data Index: 2282660 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.0754. Min Act: -0.1700

Data Index: 4057329 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.0754. Min Act: -0.1700

Data Index: 6644588 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.0754. Min Act: -0.1700

Data Index: 603547 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2014. Min Range: -3.2014

Max Act: 3.0596. Min Act: -0.1700

Data Index: 5741026 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #19