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

Dataset: Open Web Text

Neuron 2593 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: 1.4260. Min Range: -1.4260

Max Act: 1.4260. Min Act: -0.1696

Data Index: 5343882 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.4060. Min Act: -0.1700

Data Index: 7131133 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3986. Min Act: -0.1700

Data Index: 4415062 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.4001. Min Act: -0.1699

Data Index: 2411070 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3873. Min Act: -0.1700

Data Index: 2164275 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3796. Min Act: -0.1693

Data Index: 7454546 (Open Web Text)

Max Activating Token Index: 304

Text #6

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3748. Min Act: -0.1698

Data Index: 8279200 (Open Web Text)

Max Activating Token Index: 593

Text #7

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3822. Min Act: -0.1700

Data Index: 2456119 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3702. Min Act: -0.1692

Data Index: 5279864 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3661. Min Act: -0.1700

Data Index: 8738030 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3706. Min Act: -0.1669

Data Index: 6384917 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3657. Min Act: -0.1698

Data Index: 15634 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3681. Min Act: -0.1689

Data Index: 1715869 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3657. Min Act: -0.1663

Data Index: 6011965 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3667. Min Act: -0.1649

Data Index: 2683721 (Open Web Text)

Max Activating Token Index: 361

Text #15

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3597. Min Act: -0.1700

Data Index: 3915311 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3668. Min Act: -0.1700

Data Index: 7899831 (Open Web Text)

Max Activating Token Index: 45

Text #17

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3650. Min Act: -0.1700

Data Index: 1092025 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3576. Min Act: -0.1699

Data Index: 5957774 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.3599. Min Act: -0.1670

Data Index: 23575 (Open Web Text)

Max Activating Token Index: 18