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

Dataset: Open Web Text

Neuron 1527 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: 3.9848. Min Range: -3.9848

Max Act: 3.9848. Min Act: -0.1700

Data Index: 1039012 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.9160. Min Act: -0.1700

Data Index: 8663506 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.8870. Min Act: -0.1700

Data Index: 6724936 (Open Web Text)

Max Activating Token Index: 93

Text #3

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.8732. Min Act: -0.1700

Data Index: 4328133 (Open Web Text)

Max Activating Token Index: 389

Text #4

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.8177. Min Act: -0.1700

Data Index: 6134890 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.7541. Min Act: -0.1700

Data Index: 2828554 (Open Web Text)

Max Activating Token Index: 433

Text #6

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.7320. Min Act: -0.1700

Data Index: 2362350 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.7369. Min Act: -0.1700

Data Index: 3204299 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.7062. Min Act: -0.1700

Data Index: 3946767 (Open Web Text)

Max Activating Token Index: 762

Text #9

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.7084. Min Act: -0.1700

Data Index: 3119897 (Open Web Text)

Max Activating Token Index: 416

Text #10

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6905. Min Act: -0.1700

Data Index: 935782 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6913. Min Act: -0.1700

Data Index: 7356373 (Open Web Text)

Max Activating Token Index: 314

Text #12

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6675. Min Act: -0.1700

Data Index: 758331 (Open Web Text)

Max Activating Token Index: 417

Text #13

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6675. Min Act: -0.1700

Data Index: 3361642 (Open Web Text)

Max Activating Token Index: 322

Text #14

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6800. Min Act: -0.1700

Data Index: 5281981 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6734. Min Act: -0.1700

Data Index: 1721250 (Open Web Text)

Max Activating Token Index: 491

Text #16

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6828. Min Act: -0.1700

Data Index: 3134402 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6309. Min Act: -0.1700

Data Index: 349174 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6495. Min Act: -0.1700

Data Index: 2468666 (Open Web Text)

Max Activating Token Index: 182

Text #19

Max Range: 3.9848. Min Range: -3.9848

Max Act: 3.6240. Min Act: -0.1700

Data Index: 1346221 (Open Web Text)

Max Activating Token Index: 24