< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.9609. Min Act: -0.1700

Data Index: 8280823 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.9099. Min Act: -0.1693

Data Index: 5088006 (Open Web Text)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.8244. Min Act: -0.1699

Data Index: 4702645 (Open Web Text)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.8244. Min Act: -0.1700

Data Index: 4908375 (Open Web Text)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.8244. Min Act: -0.1697

Data Index: 5088007 (Open Web Text)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7900. Min Act: -0.1700

Data Index: 2171492 (Open Web Text)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7728. Min Act: -0.1700

Data Index: 2133898 (Open Web Text)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7555. Min Act: -0.1699

Data Index: 478354 (Open Web Text)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7555. Min Act: -0.1700

Data Index: 856855 (Open Web Text)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7555. Min Act: -0.1695

Data Index: 2651637 (Open Web Text)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7209. Min Act: -0.1700

Data Index: 1807915 (Open Web Text)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7036. Min Act: -0.1700

Data Index: 1892715 (Open Web Text)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7382. Min Act: -0.1700

Data Index: 1774862 (Open Web Text)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7209. Min Act: -0.1700

Data Index: 8418142 (Open Web Text)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7036. Min Act: -0.1692

Data Index: 1438890 (Open Web Text)

Max Activating Token Index: 705

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7036. Min Act: -0.1697

Data Index: 1185971 (Open Web Text)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7036. Min Act: -0.1700

Data Index: 8117523 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.6863. Min Act: -0.1689

Data Index: 5726042 (Open Web Text)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.6863. Min Act: -0.1687

Data Index: 2243894 (Open Web Text)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9609. Min Range: -1.9609

Max Act: 1.7209. Min Act: -0.1700

Data Index: 6253093 (Open Web Text)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #19