< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 14 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: 3.6332. Min Range: -3.6332

Max Act: 3.6332. Min Act: -0.1700

Data Index: 5311211 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.6332. Min Act: -0.1700

Data Index: 743116 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.6019. Min Act: -0.1700

Data Index: 3604663 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.6019. Min Act: -0.1700

Data Index: 7664975 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.6019. Min Act: -0.1700

Data Index: 532429 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.6019. Min Act: -0.1700

Data Index: 1301970 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.6019. Min Act: -0.1700

Data Index: 7592808 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.6019. Min Act: -0.1700

Data Index: 1417467 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5706. Min Act: -0.1700

Data Index: 2134444 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5706. Min Act: -0.1700

Data Index: 784580 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5706. Min Act: -0.1700

Data Index: 1601754 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5706. Min Act: -0.1700

Data Index: 4489543 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5393. Min Act: -0.1700

Data Index: 2430227 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5393. Min Act: -0.1700

Data Index: 7018696 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5393. Min Act: -0.1700

Data Index: 721148 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5393. Min Act: -0.1700

Data Index: 371554 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5393. Min Act: -0.1700

Data Index: 2744357 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5393. Min Act: -0.1700

Data Index: 924410 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5393. Min Act: -0.1700

Data Index: 2705547 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5393. Min Act: -0.1700

Data Index: 2137323 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19