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

Dataset: Open Web Text

Neuron 2831 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: 0.8833. Min Range: -0.8833

Max Act: 0.8833. Min Act: -0.1695

Data Index: 8631611 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8799. Min Act: -0.1700

Data Index: 3940792 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8819. Min Act: -0.1697

Data Index: 7142885 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8734. Min Act: -0.1691

Data Index: 5080723 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8708. Min Act: -0.1696

Data Index: 5254068 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8728. Min Act: -0.1683

Data Index: 3467417 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8552. Min Act: -0.1697

Data Index: 6851276 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8582. Min Act: -0.1696

Data Index: 4535852 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8613. Min Act: -0.1692

Data Index: 209131 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8600. Min Act: -0.1698

Data Index: 4826938 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8441. Min Act: -0.1700

Data Index: 4080916 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8538. Min Act: -0.1695

Data Index: 7510549 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8555. Min Act: -0.1700

Data Index: 1917390 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8427. Min Act: -0.1700

Data Index: 6011104 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8441. Min Act: -0.1690

Data Index: 2631524 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8528. Min Act: -0.1689

Data Index: 8292849 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8482. Min Act: -0.1597

Data Index: 782799 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8434. Min Act: -0.1700

Data Index: 2709967 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8424. Min Act: -0.1688

Data Index: 187091 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8419. Min Act: -0.1700

Data Index: 4764714 (Open Web Text)

Max Activating Token Index: 1023