< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2020 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.8390. Min Act: -0.1700

Data Index: 10067398 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.7434. Min Act: -0.1700

Data Index: 8611127 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.7114. Min Act: -0.1700

Data Index: 2487334 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.7114. Min Act: -0.1700

Data Index: 8771171 (The Pile)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6954. Min Act: -0.1700

Data Index: 980923 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6794. Min Act: -0.1700

Data Index: 10372000 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6954. Min Act: -0.1700

Data Index: 4215984 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6954. Min Act: -0.1700

Data Index: 659610 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6954. Min Act: -0.1700

Data Index: 3214381 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6954. Min Act: -0.1700

Data Index: 2928212 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.7114. Min Act: -0.1700

Data Index: 4560841 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6794. Min Act: -0.1700

Data Index: 2544359 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.7274. Min Act: -0.1700

Data Index: 7303456 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6794. Min Act: -0.1700

Data Index: 9452449 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6794. Min Act: -0.1700

Data Index: 5644326 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6634. Min Act: -0.1700

Data Index: 9643552 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6634. Min Act: -0.1700

Data Index: 4951039 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6634. Min Act: -0.1700

Data Index: 7196789 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6794. Min Act: -0.1700

Data Index: 7490447 (The Pile)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8390. Min Range: -2.8390

Max Act: 2.6313. Min Act: -0.1700

Data Index: 3501966 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #19