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

Dataset: Open Web Text

Neuron 497 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: 1.1217. Min Range: -1.1217

Max Act: 1.1141. Min Act: -0.1698

Data Index: 5058084 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.1217. Min Act: -0.1700

Data Index: 3647247 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.1090. Min Act: -0.1700

Data Index: 1617244 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.1102. Min Act: -0.1660

Data Index: 5974820 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0955. Min Act: -0.1699

Data Index: 6682427 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0955. Min Act: -0.1689

Data Index: 1725391 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0900. Min Act: -0.1700

Data Index: 5168596 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0747. Min Act: -0.1700

Data Index: 5637538 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0646. Min Act: -0.1699

Data Index: 5529422 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0615. Min Act: -0.1698

Data Index: 3275377 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0560. Min Act: -0.1697

Data Index: 2430559 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0498. Min Act: -0.1697

Data Index: 6417586 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0599. Min Act: -0.1699

Data Index: 4563923 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0538. Min Act: -0.1700

Data Index: 4815319 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0517. Min Act: -0.1700

Data Index: 8001721 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0372. Min Act: -0.1700

Data Index: 5396499 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0407. Min Act: -0.1700

Data Index: 3062667 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0406. Min Act: -0.1700

Data Index: 2628590 (Open Web Text)

Max Activating Token Index: 232

Text #18

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0491. Min Act: -0.1700

Data Index: 3168841 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.1217. Min Range: -1.1217

Max Act: 1.0406. Min Act: -0.1686

Data Index: 2702220 (Open Web Text)

Max Activating Token Index: 3