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

Dataset: Open Web Text

Neuron 1067 in Layer 6

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: 3.7112. Min Range: -3.7112

Max Act: 3.7112. Min Act: -0.1700

Data Index: 2003124 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.7058. Min Act: -0.1700

Data Index: 7860117 (Open Web Text)

Max Activating Token Index: 891

Text #2

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6929. Min Act: -0.1700

Data Index: 6455114 (Open Web Text)

Max Activating Token Index: 830

Text #3

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6839. Min Act: -0.1700

Data Index: 5281568 (Open Web Text)

Max Activating Token Index: 159

Text #4

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6767. Min Act: -0.1700

Data Index: 1991186 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6475. Min Act: -0.1700

Data Index: 6531341 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6175. Min Act: -0.1700

Data Index: 4979055 (Open Web Text)

Max Activating Token Index: 327

Text #7

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5584. Min Act: -0.1700

Data Index: 3922404 (Open Web Text)

Max Activating Token Index: 999

Text #8

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5458. Min Act: -0.1700

Data Index: 5295559 (Open Web Text)

Max Activating Token Index: 682

Text #9

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5491. Min Act: -0.1700

Data Index: 6299217 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5557. Min Act: -0.1700

Data Index: 7034940 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5557. Min Act: -0.1700

Data Index: 7864006 (Open Web Text)

Max Activating Token Index: 942

Text #12

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5310. Min Act: -0.1700

Data Index: 6270654 (Open Web Text)

Max Activating Token Index: 509

Text #13

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5210. Min Act: -0.1700

Data Index: 1630799 (Open Web Text)

Max Activating Token Index: 822

Text #14

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5412. Min Act: -0.1700

Data Index: 7039361 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5228. Min Act: -0.1700

Data Index: 7119973 (Open Web Text)

Max Activating Token Index: 747

Text #16

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5132. Min Act: -0.1700

Data Index: 7828383 (Open Web Text)

Max Activating Token Index: 811

Text #17

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5398. Min Act: -0.1700

Data Index: 6793566 (Open Web Text)

Max Activating Token Index: 1006

Text #18

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.4928. Min Act: -0.1700

Data Index: 4553980 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.4863. Min Act: -0.1700

Data Index: 7056623 (Open Web Text)

Max Activating Token Index: 486