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

Dataset: Open Web Text

Neuron 1553 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: 1.2142. Min Range: -1.2142

Max Act: 1.2142. Min Act: -0.1699

Data Index: 431351 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1872. Min Act: -0.1696

Data Index: 6297263 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1899. Min Act: -0.1699

Data Index: 5643179 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1840. Min Act: -0.1700

Data Index: 6248362 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1843. Min Act: -0.1700

Data Index: 6248358 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1746. Min Act: -0.1700

Data Index: 5437634 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1703. Min Act: -0.1691

Data Index: 1758641 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1685. Min Act: -0.1691

Data Index: 8394779 (Open Web Text)

Max Activating Token Index: 627

Text #8

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1583. Min Act: -0.1700

Data Index: 4208686 (Open Web Text)

Max Activating Token Index: 769

Text #9

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1613. Min Act: -0.1685

Data Index: 5009827 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1604. Min Act: -0.1699

Data Index: 6248353 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1683. Min Act: -0.1686

Data Index: 4123201 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1546. Min Act: -0.1700

Data Index: 8174532 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1606. Min Act: -0.1698

Data Index: 8535221 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1526. Min Act: -0.1700

Data Index: 5786180 (Open Web Text)

Max Activating Token Index: 479

Text #15

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1594. Min Act: -0.1692

Data Index: 6833990 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1508. Min Act: -0.1697

Data Index: 2171299 (Open Web Text)

Max Activating Token Index: 442

Text #17

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1578. Min Act: -0.1700

Data Index: 816571 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1548. Min Act: -0.1695

Data Index: 5533596 (Open Web Text)

Max Activating Token Index: 322

Text #19

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1501. Min Act: -0.1698

Data Index: 5615903 (Open Web Text)

Max Activating Token Index: 59