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

Dataset: Open Web Text

Neuron 92 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: 3.5991. Min Range: -3.5991

Max Act: 3.5991. Min Act: -0.1700

Data Index: 1281658 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4971. Min Act: -0.1700

Data Index: 3963235 (Open Web Text)

Max Activating Token Index: 610

Text #2

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4558. Min Act: -0.1700

Data Index: 4871899 (Open Web Text)

Max Activating Token Index: 724

Text #3

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4589. Min Act: -0.1700

Data Index: 6342812 (Open Web Text)

Max Activating Token Index: 404

Text #4

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4536. Min Act: -0.1700

Data Index: 6156905 (Open Web Text)

Max Activating Token Index: 642

Text #5

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4405. Min Act: -0.1700

Data Index: 285141 (Open Web Text)

Max Activating Token Index: 739

Text #6

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4381. Min Act: -0.1700

Data Index: 1941698 (Open Web Text)

Max Activating Token Index: 797

Text #7

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4224. Min Act: -0.1700

Data Index: 2252126 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4193. Min Act: -0.1700

Data Index: 6092812 (Open Web Text)

Max Activating Token Index: 594

Text #9

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4005. Min Act: -0.1700

Data Index: 7229821 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4051. Min Act: -0.1700

Data Index: 4606596 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4009. Min Act: -0.1700

Data Index: 2026029 (Open Web Text)

Max Activating Token Index: 903

Text #12

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4136. Min Act: -0.1700

Data Index: 583758 (Open Web Text)

Max Activating Token Index: 674

Text #13

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.3828. Min Act: -0.1700

Data Index: 7957442 (Open Web Text)

Max Activating Token Index: 96

Text #14

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.4063. Min Act: -0.1700

Data Index: 1066174 (Open Web Text)

Max Activating Token Index: 808

Text #15

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.3826. Min Act: -0.1700

Data Index: 8017428 (Open Web Text)

Max Activating Token Index: 308

Text #16

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.3974. Min Act: -0.1700

Data Index: 595156 (Open Web Text)

Max Activating Token Index: 725

Text #17

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.3740. Min Act: -0.1700

Data Index: 8456197 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.3996. Min Act: -0.1700

Data Index: 798796 (Open Web Text)

Max Activating Token Index: 211

Text #19

Max Range: 3.5991. Min Range: -3.5991

Max Act: 3.3676. Min Act: -0.1700

Data Index: 350036 (Open Web Text)

Max Activating Token Index: 418