< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.5188. Min Act: -0.1700

Data Index: 5264644 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.4563. Min Act: -0.1700

Data Index: 10459906 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.4251. Min Act: -0.1700

Data Index: 6858815 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.4251. Min Act: -0.1700

Data Index: 7670184 (The Pile)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.3625. Min Act: -0.1700

Data Index: 3839741 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.2688. Min Act: -0.1700

Data Index: 9946277 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.2375. Min Act: -0.1700

Data Index: 400957 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.1750. Min Act: -0.1700

Data Index: 1853064 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.1438. Min Act: -0.1700

Data Index: 4230214 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.1125. Min Act: -0.1700

Data Index: 10435203 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.1125. Min Act: -0.1700

Data Index: 6399085 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.1125. Min Act: -0.1700

Data Index: 1948437 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.0812. Min Act: -0.1700

Data Index: 4237547 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.0812. Min Act: -0.1700

Data Index: 2234387 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.0812. Min Act: -0.1700

Data Index: 7322320 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.0812. Min Act: -0.1700

Data Index: 6905020 (The Pile)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.0812. Min Act: -0.1700

Data Index: 2770553 (The Pile)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.0812. Min Act: -0.1700

Data Index: 7681780 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.0500. Min Act: -0.1700

Data Index: 655277 (The Pile)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.5188. Min Range: -4.5188

Max Act: 4.0500. Min Act: -0.1700

Data Index: 6552421 (The Pile)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #19