Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 0 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.1323. Min Act: -0.1700

Data Index: 5878780 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0821. Min Act: -0.1700

Data Index: 523341 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0821. Min Act: -0.1700

Data Index: 2435314 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0821. Min Act: -0.1700

Data Index: 1899723 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0821. Min Act: -0.1699

Data Index: 8190995 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0654. Min Act: -0.1700

Data Index: 416709 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0654. Min Act: -0.1700

Data Index: 7311143 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0654. Min Act: -0.1700

Data Index: 3066505 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0654. Min Act: -0.1700

Data Index: 481045 (The Pile)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0486. Min Act: -0.1700

Data Index: 3568526 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0318. Min Act: -0.1700

Data Index: 720735 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0318. Min Act: -0.1700

Data Index: 722759 (The Pile)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0149. Min Act: -0.1700

Data Index: 9301892 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9980. Min Act: -0.1700

Data Index: 7649518 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9980. Min Act: -0.1700

Data Index: 7282330 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9980. Min Act: -0.1700

Data Index: 3410906 (The Pile)

Max Activating Token Index: 629

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9980. Min Act: -0.1700

Data Index: 3470851 (The Pile)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9980. Min Act: -0.1700

Data Index: 2145239 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9980. Min Act: -0.1700

Data Index: 1384475 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9980. Min Act: -0.1700

Data Index: 10777040 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #19