< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6391 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: 7.1957. Min Range: -7.1957

Max Act: 7.1957. Min Act: -0.1700

Data Index: 1545296 (Open Web Text)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.1957. Min Range: -7.1957

Max Act: 7.1957. Min Act: -0.1700

Data Index: 1969993 (Open Web Text)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.9769. Min Act: -0.1700

Data Index: 94535 (Open Web Text)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.9457. Min Act: -0.1700

Data Index: 7935564 (Open Web Text)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.9144. Min Act: -0.1700

Data Index: 1009170 (Open Web Text)

Max Activating Token Index: 607

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.9457. Min Act: -0.1700

Data Index: 1513629 (Open Web Text)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.9144. Min Act: -0.1700

Data Index: 1142218 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.8519. Min Act: -0.1700

Data Index: 689407 (Open Web Text)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.8832. Min Act: -0.1700

Data Index: 865578 (Open Web Text)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.8832. Min Act: -0.1700

Data Index: 4797751 (Open Web Text)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.8207. Min Act: -0.1700

Data Index: 5209018 (Open Web Text)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.7582. Min Act: -0.1700

Data Index: 4771493 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.7582. Min Act: -0.1700

Data Index: 7946332 (Open Web Text)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.7582. Min Act: -0.1700

Data Index: 4952734 (Open Web Text)

Max Activating Token Index: 236

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.6957. Min Act: -0.1700

Data Index: 454741 (Open Web Text)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.7269. Min Act: -0.1700

Data Index: 7759036 (Open Web Text)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.6957. Min Act: -0.1700

Data Index: 6537245 (Open Web Text)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.6644. Min Act: -0.1700

Data Index: 7828096 (Open Web Text)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.6332. Min Act: -0.1700

Data Index: 4675914 (Open Web Text)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.1957. Min Range: -7.1957

Max Act: 6.6332. Min Act: -0.1700

Data Index: 2438104 (Open Web Text)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #19