< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3071 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.2494. Min Act: -0.1700

Data Index: 927654 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.2337. Min Act: -0.1700

Data Index: 3915871 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.2023. Min Act: -0.1700

Data Index: 7579279 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.2023. Min Act: -0.1700

Data Index: 6195419 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.2023. Min Act: -0.1700

Data Index: 3088733 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1708. Min Act: -0.1700

Data Index: 7675524 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1551. Min Act: -0.1700

Data Index: 7280966 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1551. Min Act: -0.1700

Data Index: 8871949 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1551. Min Act: -0.1700

Data Index: 2033503 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1551. Min Act: -0.1700

Data Index: 1701833 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1393. Min Act: -0.1700

Data Index: 2802021 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1393. Min Act: -0.1700

Data Index: 10589292 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1393. Min Act: -0.1700

Data Index: 6888 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1393. Min Act: -0.1700

Data Index: 10135378 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1235. Min Act: -0.1700

Data Index: 4953993 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1078. Min Act: -0.1700

Data Index: 7918702 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1078. Min Act: -0.1700

Data Index: 4580629 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.0920. Min Act: -0.1700

Data Index: 3587690 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.0920. Min Act: -0.1700

Data Index: 2243298 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.0920. Min Act: -0.1700

Data Index: 4958297 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #19