< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3017 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4983. Min Act: -0.1700

Data Index: 950479 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4983. Min Act: -0.1700

Data Index: 7690551 (The Pile)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4827. Min Act: -0.1700

Data Index: 1229831 (The Pile)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4827. Min Act: -0.1700

Data Index: 3128291 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4356. Min Act: -0.1700

Data Index: 1843510 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4356. Min Act: -0.1700

Data Index: 6295976 (The Pile)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4356. Min Act: -0.1700

Data Index: 5038533 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4356. Min Act: -0.1700

Data Index: 708246 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4356. Min Act: -0.1700

Data Index: 563417 (The Pile)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4356. Min Act: -0.1700

Data Index: 1160296 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4199. Min Act: -0.1700

Data Index: 10352854 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4043. Min Act: -0.1700

Data Index: 4388859 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4043. Min Act: -0.1700

Data Index: 156474 (The Pile)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.4043. Min Act: -0.1700

Data Index: 144533 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.3886. Min Act: -0.1700

Data Index: 5950214 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.3886. Min Act: -0.1700

Data Index: 7084911 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.3886. Min Act: -0.1700

Data Index: 6254011 (The Pile)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.3886. Min Act: -0.1700

Data Index: 9936397 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.3886. Min Act: -0.1700

Data Index: 6294006 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4983. Min Range: -3.4983

Max Act: 3.3886. Min Act: -0.1700

Data Index: 2408121 (The Pile)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #19