< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 61 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: 2.2596. Min Range: -2.2596

Max Act: 2.2596. Min Act: -0.1700

Data Index: 8670049 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.2100. Min Act: -0.1700

Data Index: 6918793 (The Pile)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.2266. Min Act: -0.1700

Data Index: 370772 (The Pile)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.2100. Min Act: -0.1700

Data Index: 8260865 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1934. Min Act: -0.1700

Data Index: 5580408 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1934. Min Act: -0.1700

Data Index: 9660549 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.2266. Min Act: -0.1700

Data Index: 2261238 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1768. Min Act: -0.1700

Data Index: 3541041 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1768. Min Act: -0.1700

Data Index: 4328860 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1435. Min Act: -0.1700

Data Index: 5325889 (The Pile)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1102. Min Act: -0.1700

Data Index: 7436795 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1602. Min Act: -0.1700

Data Index: 8831702 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1934. Min Act: -0.1700

Data Index: 6533907 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1269. Min Act: -0.1700

Data Index: 4578996 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1602. Min Act: -0.1700

Data Index: 9134758 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1768. Min Act: -0.1700

Data Index: 6775191 (The Pile)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1269. Min Act: -0.1700

Data Index: 4665327 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1102. Min Act: -0.1700

Data Index: 5136498 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1602. Min Act: -0.1700

Data Index: 2467982 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2596. Min Range: -2.2596

Max Act: 2.1602. Min Act: -0.1700

Data Index: 8977065 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #19