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

Dataset: Open Web Text

Neuron 1013 in Layer 5

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: 4.6819. Min Range: -4.6819

Max Act: 4.6819. Min Act: -0.1700

Data Index: 3125047 (Open Web Text)

Max Activating Token Index: 697

Text #1

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6559. Min Act: -0.1700

Data Index: 6608200 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6794. Min Act: -0.1700

Data Index: 1872157 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6400. Min Act: -0.1700

Data Index: 8619696 (Open Web Text)

Max Activating Token Index: 664

Text #4

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6790. Min Act: -0.1700

Data Index: 778757 (Open Web Text)

Max Activating Token Index: 985

Text #5

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6340. Min Act: -0.1700

Data Index: 6389589 (Open Web Text)

Max Activating Token Index: 893

Text #6

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.5892. Min Act: -0.1700

Data Index: 5065603 (Open Web Text)

Max Activating Token Index: 1006

Text #7

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6266. Min Act: -0.1700

Data Index: 3791860 (Open Web Text)

Max Activating Token Index: 755

Text #8

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6512. Min Act: -0.1700

Data Index: 7738880 (Open Web Text)

Max Activating Token Index: 454

Text #9

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6080. Min Act: -0.1700

Data Index: 5091157 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6069. Min Act: -0.1700

Data Index: 2548682 (Open Web Text)

Max Activating Token Index: 889

Text #11

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.5879. Min Act: -0.1700

Data Index: 6128416 (Open Web Text)

Max Activating Token Index: 921

Text #12

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6058. Min Act: -0.1700

Data Index: 7641908 (Open Web Text)

Max Activating Token Index: 683

Text #13

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.5920. Min Act: -0.1700

Data Index: 7573726 (Open Web Text)

Max Activating Token Index: 740

Text #14

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.6119. Min Act: -0.1700

Data Index: 4247505 (Open Web Text)

Max Activating Token Index: 542

Text #15

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.5632. Min Act: -0.1700

Data Index: 1626771 (Open Web Text)

Max Activating Token Index: 789

Text #16

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.5537. Min Act: -0.1700

Data Index: 6304619 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.5874. Min Act: -0.1700

Data Index: 4084449 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.5793. Min Act: -0.1700

Data Index: 6389566 (Open Web Text)

Max Activating Token Index: 736

Text #19

Max Range: 4.6819. Min Range: -4.6819

Max Act: 4.5723. Min Act: -0.1700

Data Index: 6509255 (Open Web Text)

Max Activating Token Index: 137