< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 17 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.0674. Min Range: -5.0674

Max Act: 5.0674. Min Act: -0.1700

Data Index: 4329478 (Open Web Text)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.7237. Min Act: -0.1700

Data Index: 1529515 (Open Web Text)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.6612. Min Act: -0.1700

Data Index: 8396979 (Open Web Text)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.6612. Min Act: -0.1700

Data Index: 6618038 (Open Web Text)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.6612. Min Act: -0.1700

Data Index: 6736284 (Open Web Text)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.6299. Min Act: -0.1700

Data Index: 5360340 (Open Web Text)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.5674. Min Act: -0.1700

Data Index: 4425399 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.5362. Min Act: -0.1700

Data Index: 2803264 (Open Web Text)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.5362. Min Act: -0.1700

Data Index: 1299879 (Open Web Text)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.5049. Min Act: -0.1700

Data Index: 8095052 (Open Web Text)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4736. Min Act: -0.1700

Data Index: 5195119 (Open Web Text)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4736. Min Act: -0.1700

Data Index: 6154022 (Open Web Text)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4736. Min Act: -0.1700

Data Index: 4879002 (Open Web Text)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4736. Min Act: -0.1700

Data Index: 4606399 (Open Web Text)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4736. Min Act: -0.1700

Data Index: 1813945 (Open Web Text)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4424. Min Act: -0.1700

Data Index: 7352691 (Open Web Text)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4111. Min Act: -0.1700

Data Index: 5437347 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4111. Min Act: -0.1700

Data Index: 1457974 (Open Web Text)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4111. Min Act: -0.1700

Data Index: 1586398 (Open Web Text)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.0674. Min Range: -5.0674

Max Act: 4.4111. Min Act: -0.1700

Data Index: 2319656 (Open Web Text)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #19