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

Dataset: Open Web Text

Neuron 2872 in Layer 2

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: 1.6895. Min Range: -1.6895

Max Act: 1.6895. Min Act: -0.1700

Data Index: 8421563 (Open Web Text)

Max Activating Token Index: 71

Text #1

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.6413. Min Act: -0.1697

Data Index: 5601848 (Open Web Text)

Max Activating Token Index: 706

Text #2

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.6249. Min Act: -0.1700

Data Index: 7486319 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.6173. Min Act: -0.1700

Data Index: 4538687 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5982. Min Act: -0.1700

Data Index: 4106636 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.6057. Min Act: -0.1699

Data Index: 2377540 (Open Web Text)

Max Activating Token Index: 98

Text #6

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5918. Min Act: -0.1700

Data Index: 8435815 (Open Web Text)

Max Activating Token Index: 881

Text #7

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5798. Min Act: -0.1699

Data Index: 5791575 (Open Web Text)

Max Activating Token Index: 849

Text #8

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5814. Min Act: -0.1652

Data Index: 4958440 (Open Web Text)

Max Activating Token Index: 78

Text #9

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5764. Min Act: -0.1700

Data Index: 410887 (Open Web Text)

Max Activating Token Index: 496

Text #10

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5750. Min Act: -0.1699

Data Index: 5096284 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5764. Min Act: -0.1700

Data Index: 1475183 (Open Web Text)

Max Activating Token Index: 107

Text #12

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5644. Min Act: -0.1700

Data Index: 8720123 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5603. Min Act: -0.1697

Data Index: 275665 (Open Web Text)

Max Activating Token Index: 823

Text #14

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5530. Min Act: -0.1700

Data Index: 6818302 (Open Web Text)

Max Activating Token Index: 871

Text #15

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5475. Min Act: -0.1700

Data Index: 1263420 (Open Web Text)

Max Activating Token Index: 787

Text #16

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5501. Min Act: -0.1700

Data Index: 160816 (Open Web Text)

Max Activating Token Index: 923

Text #17

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5487. Min Act: -0.1699

Data Index: 7196424 (Open Web Text)

Max Activating Token Index: 654

Text #18

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5507. Min Act: -0.1700

Data Index: 8378564 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.5596. Min Act: -0.1700

Data Index: 1609017 (Open Web Text)

Max Activating Token Index: 381