< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 5111 in Layer 15

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.7509. Min Act: -0.1700

Data Index: 3163281 (Open Web Text)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6884. Min Act: -0.1700

Data Index: 7081528 (Open Web Text)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6727. Min Act: -0.1700

Data Index: 1702437 (Open Web Text)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6727. Min Act: -0.1700

Data Index: 675190 (Open Web Text)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5945. Min Act: -0.1700

Data Index: 2924304 (Open Web Text)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5788. Min Act: -0.1700

Data Index: 5064193 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5945. Min Act: -0.1700

Data Index: 1272097 (Open Web Text)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5632. Min Act: -0.1700

Data Index: 75502 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5475. Min Act: -0.1700

Data Index: 623069 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5319. Min Act: -0.1700

Data Index: 7554833 (Open Web Text)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5319. Min Act: -0.1700

Data Index: 262337 (Open Web Text)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5162. Min Act: -0.1700

Data Index: 6218852 (Open Web Text)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5319. Min Act: -0.1700

Data Index: 1868607 (Open Web Text)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5005. Min Act: -0.1700

Data Index: 8770261 (Open Web Text)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5005. Min Act: -0.1700

Data Index: 21907 (Open Web Text)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5005. Min Act: -0.1700

Data Index: 3519848 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.4692. Min Act: -0.1700

Data Index: 770772 (Open Web Text)

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.4692. Min Act: -0.1700

Data Index: 3258514 (Open Web Text)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.4849. Min Act: -0.1700

Data Index: 7432242 (Open Web Text)

Max Activating Token Index: 967

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.4535. Min Act: -0.1700

Data Index: 3129592 (Open Web Text)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #19