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

Dataset: Open Web Text

Neuron 174 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: 1.3122. Min Range: -1.3122

Max Act: 1.3122. Min Act: -0.1700

Data Index: 1312683 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.2953. Min Act: -0.1700

Data Index: 4433855 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.2173. Min Act: -0.1700

Data Index: 4856272 (Open Web Text)

Max Activating Token Index: 439

Text #3

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.2180. Min Act: -0.1700

Data Index: 334339 (Open Web Text)

Max Activating Token Index: 549

Text #4

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.2074. Min Act: -0.1700

Data Index: 8140705 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.2081. Min Act: -0.1700

Data Index: 1287582 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.2162. Min Act: -0.1700

Data Index: 7593603 (Open Web Text)

Max Activating Token Index: 987

Text #7

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.2077. Min Act: -0.1700

Data Index: 3089961 (Open Web Text)

Max Activating Token Index: 308

Text #8

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1786. Min Act: -0.1700

Data Index: 5186988 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1911. Min Act: -0.1700

Data Index: 4111575 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1982. Min Act: -0.1699

Data Index: 3988669 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1935. Min Act: -0.1700

Data Index: 4964287 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1668. Min Act: -0.1700

Data Index: 5360978 (Open Web Text)

Max Activating Token Index: 679

Text #13

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1754. Min Act: -0.1674

Data Index: 1730575 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1627. Min Act: -0.1700

Data Index: 7695294 (Open Web Text)

Max Activating Token Index: 714

Text #15

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1599. Min Act: -0.1700

Data Index: 3272399 (Open Web Text)

Max Activating Token Index: 706

Text #16

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1616. Min Act: -0.1700

Data Index: 53704 (Open Web Text)

Max Activating Token Index: 56

Text #17

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1679. Min Act: -0.1700

Data Index: 7387180 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1621. Min Act: -0.1700

Data Index: 6175695 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1695. Min Act: -0.1700

Data Index: 478289 (Open Web Text)

Max Activating Token Index: 904