< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2015 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4957. Min Act: -0.1700

Data Index: 9988909 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4487. Min Act: -0.1700

Data Index: 5597399 (The Pile)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4643. Min Act: -0.1700

Data Index: 7377854 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4330. Min Act: -0.1700

Data Index: 4601396 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4487. Min Act: -0.1700

Data Index: 8014027 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4330. Min Act: -0.1700

Data Index: 4502479 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4173. Min Act: -0.1700

Data Index: 3222811 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4016. Min Act: -0.1700

Data Index: 4543062 (The Pile)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4330. Min Act: -0.1700

Data Index: 9323258 (The Pile)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4016. Min Act: -0.1700

Data Index: 2394293 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4016. Min Act: -0.1700

Data Index: 857485 (The Pile)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.3859. Min Act: -0.1700

Data Index: 1628128 (The Pile)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4016. Min Act: -0.1700

Data Index: 6396170 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.4016. Min Act: -0.1700

Data Index: 5443436 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.3545. Min Act: -0.1700

Data Index: 9660455 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.3702. Min Act: -0.1700

Data Index: 3779277 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.3702. Min Act: -0.1700

Data Index: 6292391 (The Pile)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.3702. Min Act: -0.1700

Data Index: 5990514 (The Pile)

Max Activating Token Index: 607

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.3859. Min Act: -0.1700

Data Index: 2603526 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4957. Min Range: -3.4957

Max Act: 3.3859. Min Act: -0.1700

Data Index: 4110744 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #19