< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 52 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.2023. Min Range: -10.2023

Max Act: 10.2023. Min Act: -0.1700

Data Index: 1804328 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.2023. Min Range: -10.2023

Max Act: 10.0148. Min Act: -0.1700

Data Index: 1845203 (Open Web Text)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.9523. Min Act: -0.1700

Data Index: 5751407 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.8273. Min Act: -0.1700

Data Index: 631695 (Open Web Text)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.7648. Min Act: -0.1700

Data Index: 6858020 (Open Web Text)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.7648. Min Act: -0.1700

Data Index: 6601846 (Open Web Text)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.7648. Min Act: -0.1700

Data Index: 2738060 (Open Web Text)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.7023. Min Act: -0.1700

Data Index: 813815 (Open Web Text)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.5148. Min Act: -0.1700

Data Index: 5773809 (Open Web Text)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.4523. Min Act: -0.1700

Data Index: 8524459 (Open Web Text)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3898. Min Act: -0.1700

Data Index: 1890299 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3898. Min Act: -0.1700

Data Index: 5090218 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3273. Min Act: -0.1700

Data Index: 8773859 (Open Web Text)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3273. Min Act: -0.1700

Data Index: 5749920 (Open Web Text)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.2648. Min Act: -0.1700

Data Index: 2320260 (Open Web Text)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3273. Min Act: -0.1700

Data Index: 7365520 (Open Web Text)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3273. Min Act: -0.1700

Data Index: 3489379 (Open Web Text)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3273. Min Act: -0.1700

Data Index: 6026529 (Open Web Text)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3273. Min Act: -0.1700

Data Index: 975603 (Open Web Text)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.2023. Min Range: -10.2023

Max Act: 9.3273. Min Act: -0.1700

Data Index: 3643284 (Open Web Text)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #19