< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 10 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.6931. Min Act: -0.1700

Data Index: 2089803 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.6305. Min Act: -0.1700

Data Index: 984060 (The Pile)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.6305. Min Act: -0.1700

Data Index: 5883722 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.5679. Min Act: -0.1700

Data Index: 5500230 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.5679. Min Act: -0.1700

Data Index: 270247 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.5522. Min Act: -0.1700

Data Index: 7134484 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.5522. Min Act: -0.1700

Data Index: 6417344 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.5365. Min Act: -0.1700

Data Index: 579892 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.5209. Min Act: -0.1700

Data Index: 10485924 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.5209. Min Act: -0.1700

Data Index: 3889980 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4895. Min Act: -0.1700

Data Index: 7008369 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4895. Min Act: -0.1700

Data Index: 3171768 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4895. Min Act: -0.1700

Data Index: 6262891 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4739. Min Act: -0.1700

Data Index: 4452979 (The Pile)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4739. Min Act: -0.1700

Data Index: 9367129 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4739. Min Act: -0.1700

Data Index: 6807196 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4739. Min Act: -0.1700

Data Index: 9647260 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4739. Min Act: -0.1700

Data Index: 1644884 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4739. Min Act: -0.1700

Data Index: 1431233 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6931. Min Range: -3.6931

Max Act: 3.4582. Min Act: -0.1700

Data Index: 8059174 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #19