< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 65 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9667. Min Act: -0.1700

Data Index: 4610780 (Open Web Text)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.8416. Min Act: -0.1700

Data Index: 1677148 (Open Web Text)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.8103. Min Act: -0.1700

Data Index: 3106822 (Open Web Text)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.7478. Min Act: -0.1700

Data Index: 2824017 (Open Web Text)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.7165. Min Act: -0.1700

Data Index: 1838455 (Open Web Text)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.7165. Min Act: -0.1700

Data Index: 5326961 (Open Web Text)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.7165. Min Act: -0.1700

Data Index: 7519608 (Open Web Text)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6852. Min Act: -0.1700

Data Index: 7710496 (Open Web Text)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6852. Min Act: -0.1700

Data Index: 7615161 (Open Web Text)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6852. Min Act: -0.1700

Data Index: 4523108 (Open Web Text)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.7165. Min Act: -0.1700

Data Index: 7820010 (Open Web Text)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6539. Min Act: -0.1700

Data Index: 8138198 (Open Web Text)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6539. Min Act: -0.1700

Data Index: 3563318 (Open Web Text)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6539. Min Act: -0.1700

Data Index: 3809053 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1958609 (Open Web Text)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6226. Min Act: -0.1700

Data Index: 8363908 (Open Web Text)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.5913. Min Act: -0.1700

Data Index: 4452809 (Open Web Text)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.5913. Min Act: -0.1700

Data Index: 7029398 (Open Web Text)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.5600. Min Act: -0.1700

Data Index: 4831106 (Open Web Text)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.5913. Min Act: -0.1700

Data Index: 943042 (Open Web Text)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #19