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

Dataset: Open Web Text

Neuron 1888 in Layer 0

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: 1.9733. Min Range: -1.9733

Max Act: 1.9733. Min Act: -0.1700

Data Index: 8286240 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.8326. Min Act: -0.1637

Data Index: 7058717 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.8255. Min Act: -0.1700

Data Index: 8496809 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.8274. Min Act: -0.1144

Data Index: 5531021 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.8113. Min Act: -0.1700

Data Index: 3717576 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.8087. Min Act: -0.1628

Data Index: 5413416 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7981. Min Act: -0.1508

Data Index: 5979585 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7847. Min Act: -0.1693

Data Index: 7013572 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7758. Min Act: -0.1642

Data Index: 1107377 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7659. Min Act: -0.1700

Data Index: 8528399 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7603. Min Act: -0.1689

Data Index: 5234092 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7607. Min Act: -0.1683

Data Index: 3924391 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7725. Min Act: -0.1573

Data Index: 6707211 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7675. Min Act: -0.1700

Data Index: 5267351 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7700. Min Act: -0.1699

Data Index: 8761273 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7664. Min Act: -0.1670

Data Index: 5536231 (Open Web Text)

Max Activating Token Index: 30

Text #16

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7609. Min Act: -0.1700

Data Index: 173878 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7608. Min Act: -0.1693

Data Index: 7025365 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7486. Min Act: -0.1687

Data Index: 2956988 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7536. Min Act: -0.1700

Data Index: 7865359 (Open Web Text)

Max Activating Token Index: 6