< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 12 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: 3.3794. Min Range: -3.3794

Max Act: 3.3794. Min Act: -0.1700

Data Index: 2084401 (The Pile)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1416111 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.3010. Min Act: -0.1700

Data Index: 7919141 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.2695. Min Act: -0.1699

Data Index: 9255640 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.2067. Min Act: -0.1699

Data Index: 7069852 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1594. Min Act: -0.1700

Data Index: 3191290 (The Pile)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1437. Min Act: -0.1700

Data Index: 2177159 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.2224. Min Act: -0.1700

Data Index: 8087321 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1279. Min Act: -0.1699

Data Index: 7383944 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1122. Min Act: -0.1700

Data Index: 5165058 (The Pile)

Max Activating Token Index: 705

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1437. Min Act: -0.1700

Data Index: 3418338 (The Pile)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.0491. Min Act: -0.1700

Data Index: 211661 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1437. Min Act: -0.1699

Data Index: 2826242 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1122. Min Act: -0.1700

Data Index: 8024824 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.0964. Min Act: -0.1700

Data Index: 8964698 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.0806. Min Act: -0.1700

Data Index: 1873173 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1279. Min Act: -0.1700

Data Index: 1493654 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1122. Min Act: -0.1700

Data Index: 3108705 (The Pile)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.0649. Min Act: -0.1700

Data Index: 8755170 (The Pile)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.1122. Min Act: -0.1700

Data Index: 7387180 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #19