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

Dataset: Open Web Text

Neuron 67 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: 1.1331. Min Range: -1.1331

Max Act: 1.1331. Min Act: -0.1697

Data Index: 4051562 (Open Web Text)

Max Activating Token Index: 956

Text #1

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1198. Min Act: -0.1677

Data Index: 4718673 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1130. Min Act: -0.1700

Data Index: 291359 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1083. Min Act: -0.1624

Data Index: 25409 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1129. Min Act: -0.1699

Data Index: 1777773 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0986. Min Act: -0.1321

Data Index: 3986153 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0991. Min Act: -0.1499

Data Index: 1944439 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0930. Min Act: -0.1477

Data Index: 38322 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1073. Min Act: -0.1699

Data Index: 3459045 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0991. Min Act: -0.1687

Data Index: 6714736 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1016. Min Act: -0.1664

Data Index: 6394665 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0991. Min Act: -0.1626

Data Index: 595985 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1050. Min Act: -0.1668

Data Index: 2831332 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1036. Min Act: -0.1691

Data Index: 6281326 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0991. Min Act: -0.1494

Data Index: 2578595 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0991. Min Act: -0.1693

Data Index: 2340235 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1035. Min Act: -0.1470

Data Index: 2225372 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1057. Min Act: -0.1684

Data Index: 5979539 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0988. Min Act: -0.1697

Data Index: 7913456 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.0866. Min Act: -0.1700

Data Index: 8829234 (Open Web Text)

Max Activating Token Index: 5