< Prev | Home | Model | Random | Next >

Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 4070 in Layer 13

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.3410. Min Act: -0.1700

Data Index: 7407061 (Open Web Text)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.3253. Min Act: -0.1700

Data Index: 5339930 (Open Web Text)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.3096. Min Act: -0.1700

Data Index: 8224690 (Open Web Text)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2311. Min Act: -0.1700

Data Index: 1000483 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1997. Min Act: -0.1700

Data Index: 1634042 (Open Web Text)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1682. Min Act: -0.1700

Data Index: 6245424 (Open Web Text)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1839. Min Act: -0.1700

Data Index: 2021161 (Open Web Text)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1525. Min Act: -0.1700

Data Index: 999387 (Open Web Text)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1682. Min Act: -0.1700

Data Index: 1037979 (Open Web Text)

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1525. Min Act: -0.1700

Data Index: 3575806 (Open Web Text)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1367. Min Act: -0.1700

Data Index: 8531359 (Open Web Text)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1052. Min Act: -0.1700

Data Index: 1916317 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0737. Min Act: -0.1700

Data Index: 7329366 (Open Web Text)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1283714 (Open Web Text)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0895. Min Act: -0.1700

Data Index: 2453617 (Open Web Text)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0895. Min Act: -0.1700

Data Index: 8714801 (Open Web Text)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0895. Min Act: -0.1700

Data Index: 711120 (Open Web Text)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0737. Min Act: -0.1700

Data Index: 5868989 (Open Web Text)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0579. Min Act: -0.1700

Data Index: 1750174 (Open Web Text)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0579. Min Act: -0.1700

Data Index: 6569889 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #19