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

Dataset: Open Web Text

Neuron 3049 in Layer 3

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: 3.5859. Min Range: -3.5859

Max Act: 3.5859. Min Act: -0.1275

Data Index: 2443566 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.5757. Min Act: -0.0786

Data Index: 2766065 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4770. Min Act: -0.1032

Data Index: 4488162 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4690. Min Act: -0.0749

Data Index: 5158851 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4611. Min Act: -0.0954

Data Index: 725958 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4375. Min Act: -0.0749

Data Index: 5002599 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4207. Min Act: -0.1042

Data Index: 7640756 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4451. Min Act: -0.0768

Data Index: 1734322 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4426. Min Act: -0.0749

Data Index: 6773195 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4044. Min Act: -0.0975

Data Index: 1898755 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3852. Min Act: -0.1228

Data Index: 6630812 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3793. Min Act: -0.0749

Data Index: 7896718 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3788. Min Act: -0.0749

Data Index: 1775539 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3284. Min Act: -0.1040

Data Index: 6320426 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3431. Min Act: -0.0749

Data Index: 4837462 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3472. Min Act: -0.0749

Data Index: 5892863 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3354. Min Act: -0.0971

Data Index: 6311745 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3137. Min Act: -0.0749

Data Index: 7218766 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3000. Min Act: -0.1158

Data Index: 2615559 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3229. Min Act: -0.0749

Data Index: 4284963 (Open Web Text)

Max Activating Token Index: 1023