< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 11 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.8672. Min Act: -0.1700

Data Index: 1034045 (Open Web Text)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.5234. Min Act: -0.1700

Data Index: 7903528 (Open Web Text)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.4609. Min Act: -0.1700

Data Index: 3682559 (Open Web Text)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.3984. Min Act: -0.1700

Data Index: 5458354 (Open Web Text)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.3359. Min Act: -0.1700

Data Index: 3069332 (Open Web Text)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2734. Min Act: -0.1700

Data Index: 4600671 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2734. Min Act: -0.1700

Data Index: 2823297 (Open Web Text)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2422. Min Act: -0.1700

Data Index: 6212415 (Open Web Text)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2422. Min Act: -0.1700

Data Index: 2371714 (Open Web Text)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2422. Min Act: -0.1700

Data Index: 4603201 (Open Web Text)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2422. Min Act: -0.1700

Data Index: 5458357 (Open Web Text)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2422. Min Act: -0.1700

Data Index: 141437 (Open Web Text)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2422. Min Act: -0.1700

Data Index: 7874102 (Open Web Text)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2109. Min Act: -0.1700

Data Index: 6515235 (Open Web Text)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2109. Min Act: -0.1700

Data Index: 3461125 (Open Web Text)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2109. Min Act: -0.1700

Data Index: 7335002 (Open Web Text)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.2109. Min Act: -0.1700

Data Index: 5651778 (Open Web Text)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.1797. Min Act: -0.1700

Data Index: 2159541 (Open Web Text)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.1797. Min Act: -0.1700

Data Index: 5708052 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.8672. Min Range: -6.8672

Max Act: 6.1484. Min Act: -0.1700

Data Index: 11293 (Open Web Text)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #19