Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 526 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.9748. Min Act: -0.1700

Data Index: 6316577 (Open Web Text)

Max Activating Token Index: 261

Text #1

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.9113. Min Act: -0.1700

Data Index: 1837952 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.9033. Min Act: -0.1700

Data Index: 2058733 (Open Web Text)

Max Activating Token Index: 1010

Text #3

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.8777. Min Act: -0.1700

Data Index: 7596188 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.8237. Min Act: -0.1700

Data Index: 3190752 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.7482. Min Act: -0.1700

Data Index: 1856082 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.8092. Min Act: -0.1700

Data Index: 8633045 (Open Web Text)

Max Activating Token Index: 369

Text #7

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.7509. Min Act: -0.1700

Data Index: 6989639 (Open Web Text)

Max Activating Token Index: 364

Text #8

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.7753. Min Act: -0.1700

Data Index: 3894564 (Open Web Text)

Max Activating Token Index: 979

Text #9

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.7724. Min Act: -0.1700

Data Index: 417085 (Open Web Text)

Max Activating Token Index: 733

Text #10

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.7250. Min Act: -0.1700

Data Index: 8562398 (Open Web Text)

Max Activating Token Index: 259

Text #11

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6669. Min Act: -0.1700

Data Index: 8702762 (Open Web Text)

Max Activating Token Index: 782

Text #12

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6581. Min Act: -0.1700

Data Index: 2357498 (Open Web Text)

Max Activating Token Index: 811

Text #13

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6835. Min Act: -0.1700

Data Index: 1058615 (Open Web Text)

Max Activating Token Index: 470

Text #14

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6476. Min Act: -0.1700

Data Index: 3112767 (Open Web Text)

Max Activating Token Index: 856

Text #15

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6700. Min Act: -0.1700

Data Index: 1049685 (Open Web Text)

Max Activating Token Index: 857

Text #16

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6454. Min Act: -0.1700

Data Index: 8258932 (Open Web Text)

Max Activating Token Index: 283

Text #17

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6654. Min Act: -0.1700

Data Index: 4061153 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6284. Min Act: -0.1700

Data Index: 807721 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 4.9748. Min Range: -4.9748

Max Act: 4.6516. Min Act: -0.1700

Data Index: 360157 (Open Web Text)

Max Activating Token Index: 27