< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 67 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.9738. Min Range: -10.9738

Max Act: 10.9738. Min Act: -0.1700

Data Index: 6500829 (Open Web Text)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.9738. Min Range: -10.9738

Max Act: 10.8488. Min Act: -0.1700

Data Index: 8356025 (Open Web Text)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.9738. Min Act: -0.1700

Data Index: 8285861 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.8488. Min Act: -0.1700

Data Index: 2121466 (Open Web Text)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.8488. Min Act: -0.1700

Data Index: 8285867 (Open Web Text)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.5363. Min Act: -0.1700

Data Index: 1783451 (Open Web Text)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.5363. Min Act: -0.1700

Data Index: 7460662 (Open Web Text)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.5363. Min Act: -0.1700

Data Index: 1904132 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.4113. Min Act: -0.1700

Data Index: 5822662 (Open Web Text)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.2863. Min Act: -0.1700

Data Index: 6701059 (Open Web Text)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.3488. Min Act: -0.1700

Data Index: 1111408 (Open Web Text)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.3488. Min Act: -0.1700

Data Index: 8356026 (Open Web Text)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.2863. Min Act: -0.1700

Data Index: 4110250 (Open Web Text)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.2863. Min Act: -0.1700

Data Index: 952537 (Open Web Text)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.1613. Min Act: -0.1700

Data Index: 5842620 (Open Web Text)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.2238. Min Act: -0.1700

Data Index: 1111406 (Open Web Text)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.0988. Min Act: -0.1700

Data Index: 6701068 (Open Web Text)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.0988. Min Act: -0.1700

Data Index: 1012487 (Open Web Text)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.0363. Min Act: -0.1700

Data Index: 778698 (Open Web Text)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.9738. Min Range: -10.9738

Max Act: 9.0363. Min Act: -0.1700

Data Index: 3011650 (Open Web Text)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #19