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

Dataset: Open Web Text

Neuron 2183 in Layer 0

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: 4.1654. Min Range: -4.1654

Max Act: 4.1654. Min Act: -0.1700

Data Index: 7781032 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.1238. Min Act: -0.1700

Data Index: 664767 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.1240. Min Act: -0.1700

Data Index: 8614851 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.1274. Min Act: -0.1700

Data Index: 4224457 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0907. Min Act: -0.1700

Data Index: 430596 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0873. Min Act: -0.1700

Data Index: 610383 (Open Web Text)

Max Activating Token Index: 761

Text #6

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.1067. Min Act: -0.1700

Data Index: 1740301 (Open Web Text)

Max Activating Token Index: 720

Text #7

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0868. Min Act: -0.1700

Data Index: 3161296 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0851. Min Act: -0.1700

Data Index: 1071924 (Open Web Text)

Max Activating Token Index: 955

Text #9

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0574. Min Act: -0.1700

Data Index: 1285913 (Open Web Text)

Max Activating Token Index: 801

Text #10

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0639. Min Act: -0.1700

Data Index: 4810645 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0557. Min Act: -0.1700

Data Index: 8315324 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0773. Min Act: -0.1700

Data Index: 7641356 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0683. Min Act: -0.1700

Data Index: 8757637 (Open Web Text)

Max Activating Token Index: 904

Text #14

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0681. Min Act: -0.1700

Data Index: 7241440 (Open Web Text)

Max Activating Token Index: 495

Text #15

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0756. Min Act: -0.1700

Data Index: 3075929 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0152. Min Act: -0.1700

Data Index: 5333400 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0417. Min Act: -0.1700

Data Index: 1300221 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0142. Min Act: -0.1700

Data Index: 6222031 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 4.1654. Min Range: -4.1654

Max Act: 4.0218. Min Act: -0.1700

Data Index: 2440099 (Open Web Text)

Max Activating Token Index: 988