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

Dataset: Open Web Text

Neuron 1629 in Layer 2

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: 3.3396. Min Range: -3.3396

Max Act: 3.3396. Min Act: -0.1700

Data Index: 8118977 (Open Web Text)

Max Activating Token Index: 232

Text #1

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.2219. Min Act: -0.1700

Data Index: 285706 (Open Web Text)

Max Activating Token Index: 701

Text #2

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.2052. Min Act: -0.1700

Data Index: 4817798 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.1860. Min Act: -0.1700

Data Index: 1950645 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.1277. Min Act: -0.1700

Data Index: 8802739 (Open Web Text)

Max Activating Token Index: 439

Text #5

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0892. Min Act: -0.1700

Data Index: 6953115 (Open Web Text)

Max Activating Token Index: 646

Text #6

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0966. Min Act: -0.1700

Data Index: 6661229 (Open Web Text)

Max Activating Token Index: 889

Text #7

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0951. Min Act: -0.1700

Data Index: 5605391 (Open Web Text)

Max Activating Token Index: 737

Text #8

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0800. Min Act: -0.1700

Data Index: 1928193 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0862. Min Act: -0.1700

Data Index: 4975810 (Open Web Text)

Max Activating Token Index: 339

Text #10

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0791. Min Act: -0.1700

Data Index: 532796 (Open Web Text)

Max Activating Token Index: 1016

Text #11

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0220. Min Act: -0.1700

Data Index: 590849 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0510. Min Act: -0.1700

Data Index: 4818457 (Open Web Text)

Max Activating Token Index: 250

Text #13

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0372. Min Act: -0.1700

Data Index: 3340295 (Open Web Text)

Max Activating Token Index: 948

Text #14

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0558. Min Act: -0.1700

Data Index: 7915061 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0324. Min Act: -0.1700

Data Index: 5605100 (Open Web Text)

Max Activating Token Index: 804

Text #16

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0271. Min Act: -0.1700

Data Index: 6620255 (Open Web Text)

Max Activating Token Index: 125

Text #17

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0230. Min Act: -0.1700

Data Index: 5662219 (Open Web Text)

Max Activating Token Index: 43

Text #18

Max Range: 3.3396. Min Range: -3.3396

Max Act: 3.0194. Min Act: -0.1700

Data Index: 456607 (Open Web Text)

Max Activating Token Index: 432

Text #19

Max Range: 3.3396. Min Range: -3.3396

Max Act: 2.9868. Min Act: -0.1700

Data Index: 1592242 (Open Web Text)

Max Activating Token Index: 32