< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3063 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1092. Min Range: -3.1092

Max Act: 3.1092. Min Act: -0.1700

Data Index: 4850141 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9829. Min Act: -0.1700

Data Index: 1353512 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9829. Min Act: -0.1700

Data Index: 4856304 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9670. Min Act: -0.1700

Data Index: 7364989 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9512. Min Act: -0.1700

Data Index: 4922846 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9354. Min Act: -0.1700

Data Index: 10791459 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9037. Min Act: -0.1700

Data Index: 3196815 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8719. Min Act: -0.1700

Data Index: 3702881 (The Pile)

Max Activating Token Index: 981

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8719. Min Act: -0.1700

Data Index: 7973255 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8719. Min Act: -0.1700

Data Index: 4541563 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8719. Min Act: -0.1700

Data Index: 7673428 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8560. Min Act: -0.1700

Data Index: 8732035 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8560. Min Act: -0.1700

Data Index: 8844706 (The Pile)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8560. Min Act: -0.1700

Data Index: 1718188 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8401. Min Act: -0.1700

Data Index: 9069269 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8401. Min Act: -0.1700

Data Index: 6782723 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8401. Min Act: -0.1700

Data Index: 9768227 (The Pile)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8401. Min Act: -0.1700

Data Index: 10455012 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8401. Min Act: -0.1700

Data Index: 5682325 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8242. Min Act: -0.1700

Data Index: 6505379 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #19