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

Dataset: Open Web Text

Neuron 2804 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: 1.0119. Min Range: -1.0119

Max Act: 1.0037. Min Act: -0.1693

Data Index: 2969030 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 1.0119. Min Range: -1.0119

Max Act: 1.0119. Min Act: -0.1697

Data Index: 4518315 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9853. Min Act: -0.1662

Data Index: 2505154 (Open Web Text)

Max Activating Token Index: 123

Text #3

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9921. Min Act: -0.1692

Data Index: 2676855 (Open Web Text)

Max Activating Token Index: 621

Text #4

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9750. Min Act: -0.1699

Data Index: 107636 (Open Web Text)

Max Activating Token Index: 86

Text #5

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9813. Min Act: -0.1687

Data Index: 170575 (Open Web Text)

Max Activating Token Index: 997

Text #6

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9738. Min Act: -0.1696

Data Index: 142459 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9761. Min Act: -0.1700

Data Index: 1840924 (Open Web Text)

Max Activating Token Index: 368

Text #8

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9627. Min Act: -0.1582

Data Index: 8452473 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9581. Min Act: -0.1687

Data Index: 7851097 (Open Web Text)

Max Activating Token Index: 189

Text #10

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9616. Min Act: -0.1595

Data Index: 4850744 (Open Web Text)

Max Activating Token Index: 54

Text #11

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9667. Min Act: -0.1653

Data Index: 2853688 (Open Web Text)

Max Activating Token Index: 479

Text #12

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9668. Min Act: -0.1689

Data Index: 6654775 (Open Web Text)

Max Activating Token Index: 659

Text #13

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9566. Min Act: -0.1685

Data Index: 829386 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9522. Min Act: -0.1696

Data Index: 1563374 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9513. Min Act: -0.1698

Data Index: 1556561 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9367. Min Act: -0.1689

Data Index: 1193517 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9412. Min Act: -0.1649

Data Index: 6884208 (Open Web Text)

Max Activating Token Index: 701

Text #18

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9421. Min Act: -0.1699

Data Index: 1940222 (Open Web Text)

Max Activating Token Index: 352

Text #19

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9291. Min Act: -0.1699

Data Index: 4937764 (Open Web Text)

Max Activating Token Index: 723