< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 40 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1667. Min Act: -0.1700

Data Index: 2419510 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1355. Min Act: -0.1700

Data Index: 5396954 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 8001643 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 4568582 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 2345814 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 7707336 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 3339556 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 7061387 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 6728224 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 6650557 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0730. Min Act: -0.1700

Data Index: 4309340 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 2728670 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0730. Min Act: -0.1700

Data Index: 152153 (Open Web Text)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0730. Min Act: -0.1700

Data Index: 4485669 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1042. Min Act: -0.1700

Data Index: 5433110 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0730. Min Act: -0.1700

Data Index: 2521361 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0417. Min Act: -0.1700

Data Index: 2475728 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0417. Min Act: -0.1700

Data Index: 2519702 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0417. Min Act: -0.1700

Data Index: 4741600 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.0417. Min Act: -0.1700

Data Index: 4957937 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #19