< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 45 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: 2.0524. Min Range: -2.0524

Max Act: 2.0524. Min Act: -0.1700

Data Index: 4413443 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.0524. Min Range: -2.0524

Max Act: 2.0187. Min Act: -0.1700

Data Index: 3357920 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.0524. Min Range: -2.0524

Max Act: 2.0187. Min Act: -0.1700

Data Index: 8380610 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.0524. Min Range: -2.0524

Max Act: 2.0019. Min Act: -0.1700

Data Index: 5886322 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9511. Min Act: -0.1700

Data Index: 3328280 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9511. Min Act: -0.1700

Data Index: 842740 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9341. Min Act: -0.1700

Data Index: 8506558 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9341. Min Act: -0.1700

Data Index: 4519068 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9170. Min Act: -0.1700

Data Index: 5527751 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9170. Min Act: -0.1700

Data Index: 2154960 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9170. Min Act: -0.1700

Data Index: 462441 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9000. Min Act: -0.1700

Data Index: 5334135 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8829. Min Act: -0.1700

Data Index: 6758498 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8829. Min Act: -0.1700

Data Index: 1758317 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8829. Min Act: -0.1696

Data Index: 7817926 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8829. Min Act: -0.1700

Data Index: 7625058 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8829. Min Act: -0.1700

Data Index: 2244532 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8658. Min Act: -0.1700

Data Index: 4605231 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8658. Min Act: -0.1700

Data Index: 4089858 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8658. Min Act: -0.1700

Data Index: 4352266 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19