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

Dataset: Open Web Text

Neuron 630 in Layer 3

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: 1.2761. Min Range: -1.2761

Max Act: 1.2761. Min Act: -0.1700

Data Index: 1765476 (Open Web Text)

Max Activating Token Index: 955

Text #1

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2300. Min Act: -0.1700

Data Index: 5210282 (Open Web Text)

Max Activating Token Index: 451

Text #2

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2418. Min Act: -0.1700

Data Index: 2769796 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2558. Min Act: -0.1700

Data Index: 5663873 (Open Web Text)

Max Activating Token Index: 897

Text #4

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2273. Min Act: -0.1699

Data Index: 7494 (Open Web Text)

Max Activating Token Index: 962

Text #5

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2246. Min Act: -0.1700

Data Index: 5758086 (Open Web Text)

Max Activating Token Index: 87

Text #6

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2012. Min Act: -0.1700

Data Index: 7496847 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2047. Min Act: -0.1700

Data Index: 1559594 (Open Web Text)

Max Activating Token Index: 894

Text #8

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2083. Min Act: -0.1700

Data Index: 1312138 (Open Web Text)

Max Activating Token Index: 876

Text #9

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1860. Min Act: -0.1700

Data Index: 572418 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1985. Min Act: -0.1700

Data Index: 4588373 (Open Web Text)

Max Activating Token Index: 868

Text #11

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1859. Min Act: -0.1700

Data Index: 407627 (Open Web Text)

Max Activating Token Index: 817

Text #12

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1874. Min Act: -0.1700

Data Index: 7406415 (Open Web Text)

Max Activating Token Index: 914

Text #13

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1760. Min Act: -0.1700

Data Index: 1850826 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1639. Min Act: -0.1700

Data Index: 8302324 (Open Web Text)

Max Activating Token Index: 868

Text #15

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1853. Min Act: -0.1699

Data Index: 7331089 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1791. Min Act: -0.1700

Data Index: 2846316 (Open Web Text)

Max Activating Token Index: 583

Text #17

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1733. Min Act: -0.1698

Data Index: 7543317 (Open Web Text)

Max Activating Token Index: 80

Text #18

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1688. Min Act: -0.1700

Data Index: 2484034 (Open Web Text)

Max Activating Token Index: 979

Text #19

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1706. Min Act: -0.1700

Data Index: 1968555 (Open Web Text)

Max Activating Token Index: 828