< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1993 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: 2.5676. Min Range: -2.5676

Max Act: 2.5676. Min Act: -0.1700

Data Index: 9952961 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5676. Min Act: -0.1700

Data Index: 10290107 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5676. Min Act: -0.1700

Data Index: 1102125 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5515. Min Act: -0.1700

Data Index: 2924721 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5676. Min Act: -0.1700

Data Index: 8428101 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5353. Min Act: -0.1700

Data Index: 3672111 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5515. Min Act: -0.1700

Data Index: 402431 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5353. Min Act: -0.1700

Data Index: 2777487 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5515. Min Act: -0.1700

Data Index: 1874389 (The Pile)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5353. Min Act: -0.1700

Data Index: 3376426 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5676. Min Act: -0.1700

Data Index: 4679677 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5515. Min Act: -0.1700

Data Index: 1965695 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5515. Min Act: -0.1700

Data Index: 7849413 (The Pile)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5191. Min Act: -0.1700

Data Index: 3890666 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5353. Min Act: -0.1700

Data Index: 2485065 (The Pile)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5353. Min Act: -0.1700

Data Index: 8385129 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5191. Min Act: -0.1700

Data Index: 2564988 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5191. Min Act: -0.1700

Data Index: 5948544 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5191. Min Act: -0.1700

Data Index: 3522739 (The Pile)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5676. Min Range: -2.5676

Max Act: 2.5191. Min Act: -0.1700

Data Index: 3923973 (The Pile)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #19