< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 8 in Layer 33

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.9825. Min Act: -0.1700

Data Index: 7880636 (Open Web Text)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.8262. Min Act: -0.1700

Data Index: 4813108 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.8575. Min Act: -0.1700

Data Index: 7177878 (Open Web Text)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.7950. Min Act: -0.1700

Data Index: 5829221 (Open Web Text)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.7950. Min Act: -0.1700

Data Index: 6098414 (Open Web Text)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.7637. Min Act: -0.1700

Data Index: 3932416 (Open Web Text)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.7325. Min Act: -0.1700

Data Index: 6628057 (Open Web Text)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.7012. Min Act: -0.1700

Data Index: 3932412 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.6700. Min Act: -0.1700

Data Index: 1352261 (Open Web Text)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.6700. Min Act: -0.1700

Data Index: 3284262 (Open Web Text)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.6387. Min Act: -0.1700

Data Index: 1314437 (Open Web Text)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.6387. Min Act: -0.1700

Data Index: 1497179 (Open Web Text)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.6075. Min Act: -0.1700

Data Index: 756754 (Open Web Text)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.5762. Min Act: -0.1700

Data Index: 8181708 (Open Web Text)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.5762. Min Act: -0.1700

Data Index: 6628056 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.5450. Min Act: -0.1700

Data Index: 2992059 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.5762. Min Act: -0.1700

Data Index: 7466894 (Open Web Text)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.4825. Min Act: -0.1700

Data Index: 2038350 (Open Web Text)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.5137. Min Act: -0.1700

Data Index: 2496572 (Open Web Text)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.9825. Min Range: -6.9825

Max Act: 6.5137. Min Act: -0.1700

Data Index: 6883975 (Open Web Text)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #19