< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 24 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')



Text #0

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.6810. Min Act: -0.1700

Data Index: 2512497 (Open Web Text)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.4931. Min Act: -0.1700

Data Index: 7918621 (Open Web Text)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.4305. Min Act: -0.1700

Data Index: 1665013 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3834. Min Act: -0.1700

Data Index: 2268717 (Open Web Text)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3991. Min Act: -0.1700

Data Index: 6879300 (Open Web Text)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3834. Min Act: -0.1700

Data Index: 764011 (Open Web Text)

Max Activating Token Index: 97

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3991. Min Act: -0.1700

Data Index: 8208971 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3677. Min Act: -0.1700

Data Index: 6275384 (Open Web Text)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3521. Min Act: -0.1700

Data Index: 1412682 (Open Web Text)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3207. Min Act: -0.1700

Data Index: 3528693 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3364. Min Act: -0.1700

Data Index: 4096239 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3050. Min Act: -0.1700

Data Index: 3100606 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3050. Min Act: -0.1700

Data Index: 6333764 (Open Web Text)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.3207. Min Act: -0.1700

Data Index: 8030623 (Open Web Text)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.2893. Min Act: -0.1700

Data Index: 1790731 (Open Web Text)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.2893. Min Act: -0.1700

Data Index: 3976057 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.2736. Min Act: -0.1700

Data Index: 1876581 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.2736. Min Act: -0.1700

Data Index: 5668530 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.2736. Min Act: -0.1700

Data Index: 1463387 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6810. Min Range: -3.6810

Max Act: 3.2736. Min Act: -0.1700

Data Index: 1700832 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19