< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 65 in Layer 12

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.4353. Min Act: -0.1700

Data Index: 4783729 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3412. Min Act: -0.1700

Data Index: 1094381 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3255. Min Act: -0.1700

Data Index: 1606017 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3255. Min Act: -0.1700

Data Index: 1481205 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3255. Min Act: -0.1700

Data Index: 9956115 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3098. Min Act: -0.1700

Data Index: 7711150 (The Pile)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3098. Min Act: -0.1700

Data Index: 3190983 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3098. Min Act: -0.1700

Data Index: 3508516 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3098. Min Act: -0.1700

Data Index: 102086 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3098. Min Act: -0.1700

Data Index: 1063717 (The Pile)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3098. Min Act: -0.1700

Data Index: 3192083 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3098. Min Act: -0.1700

Data Index: 9073353 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.3098. Min Act: -0.1700

Data Index: 10282275 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.2941. Min Act: -0.1700

Data Index: 6064400 (The Pile)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.2941. Min Act: -0.1700

Data Index: 4891336 (The Pile)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.2941. Min Act: -0.1700

Data Index: 1659945 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.2784. Min Act: -0.1700

Data Index: 4256193 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.2784. Min Act: -0.1700

Data Index: 6479860 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.2784. Min Act: -0.1700

Data Index: 10034922 (The Pile)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4353. Min Range: -3.4353

Max Act: 3.2784. Min Act: -0.1700

Data Index: 263624 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #19