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

Dataset: Open Web Text

Neuron 2708 in Layer 1

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: 2.8878. Min Range: -2.8878

Max Act: 2.8878. Min Act: -0.1700

Data Index: 633494 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8183. Min Act: -0.1700

Data Index: 8026858 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8183. Min Act: -0.1700

Data Index: 2254595 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8004. Min Act: -0.1700

Data Index: 7377609 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8004. Min Act: -0.1700

Data Index: 6743044 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8004. Min Act: -0.1700

Data Index: 6012107 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7977. Min Act: -0.1700

Data Index: 3565937 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8004. Min Act: -0.1700

Data Index: 5416344 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8004. Min Act: -0.1700

Data Index: 2806668 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7892. Min Act: -0.1700

Data Index: 179873 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7617. Min Act: -0.1700

Data Index: 5417087 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7804. Min Act: -0.1700

Data Index: 3541440 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7804. Min Act: -0.1700

Data Index: 3701977 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7617. Min Act: -0.1700

Data Index: 719853 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7617. Min Act: -0.1700

Data Index: 6591816 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7804. Min Act: -0.1700

Data Index: 1746045 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7617. Min Act: -0.1700

Data Index: 6349294 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7617. Min Act: -0.1700

Data Index: 247384 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7804. Min Act: -0.1700

Data Index: 5426642 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7721. Min Act: -0.1700

Data Index: 50561 (Open Web Text)

Max Activating Token Index: 5