< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 46 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8862. Min Act: -0.1700

Data Index: 790717 (The Pile)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.9175. Min Act: -0.1700

Data Index: 5010004 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.9175. Min Act: -0.1700

Data Index: 6673426 (The Pile)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.9800. Min Act: -0.1700

Data Index: 7933530 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.9488. Min Act: -0.1700

Data Index: 3359205 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8550. Min Act: -0.1700

Data Index: 6605157 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8550. Min Act: -0.1700

Data Index: 825203 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.7924. Min Act: -0.1700

Data Index: 3499862 (The Pile)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8550. Min Act: -0.1700

Data Index: 5866167 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8550. Min Act: -0.1700

Data Index: 4360644 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8237. Min Act: -0.1700

Data Index: 4651662 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8862. Min Act: -0.1700

Data Index: 1697276 (The Pile)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.7924. Min Act: -0.1700

Data Index: 3369799 (The Pile)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8237. Min Act: -0.1700

Data Index: 9909655 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8237. Min Act: -0.1700

Data Index: 6576651 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.7924. Min Act: -0.1700

Data Index: 8446179 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.6046. Min Act: -0.1700

Data Index: 4001259 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8237. Min Act: -0.1700

Data Index: 2648395 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.7924. Min Act: -0.1700

Data Index: 3179186 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.8237. Min Act: -0.1700

Data Index: 3686546 (The Pile)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #19