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

Dataset: Open Web Text

Neuron 1536 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: 6.0796. Min Range: -6.0796

Max Act: 6.0796. Min Act: -0.1699

Data Index: 6950763 (Open Web Text)

Max Activating Token Index: 411

Text #1

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.9176. Min Act: -0.1700

Data Index: 7094787 (Open Web Text)

Max Activating Token Index: 641

Text #2

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.6421. Min Act: -0.1700

Data Index: 8590307 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.6290. Min Act: -0.1700

Data Index: 907572 (Open Web Text)

Max Activating Token Index: 339

Text #4

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.6009. Min Act: -0.1700

Data Index: 8779308 (Open Web Text)

Max Activating Token Index: 772

Text #5

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.3000. Min Act: -0.1700

Data Index: 6462911 (Open Web Text)

Max Activating Token Index: 577

Text #6

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.6070. Min Act: -0.1700

Data Index: 854416 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.4541. Min Act: -0.1700

Data Index: 470604 (Open Web Text)

Max Activating Token Index: 1019

Text #8

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.5909. Min Act: -0.1700

Data Index: 7989697 (Open Web Text)

Max Activating Token Index: 896

Text #9

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.5110. Min Act: -0.1700

Data Index: 8508582 (Open Web Text)

Max Activating Token Index: 895

Text #10

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.6760. Min Act: -0.1700

Data Index: 4348803 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.3727. Min Act: -0.1700

Data Index: 869023 (Open Web Text)

Max Activating Token Index: 232

Text #12

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.3568. Min Act: -0.1700

Data Index: 1888389 (Open Web Text)

Max Activating Token Index: 309

Text #13

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.5787. Min Act: -0.1700

Data Index: 1847782 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.5791. Min Act: -0.1700

Data Index: 162399 (Open Web Text)

Max Activating Token Index: 809

Text #15

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.4239. Min Act: -0.1700

Data Index: 8614694 (Open Web Text)

Max Activating Token Index: 517

Text #16

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.5056. Min Act: -0.1700

Data Index: 1785167 (Open Web Text)

Max Activating Token Index: 847

Text #17

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.5878. Min Act: -0.1700

Data Index: 5402238 (Open Web Text)

Max Activating Token Index: 582

Text #18

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.5242. Min Act: -0.1700

Data Index: 5103814 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 6.0796. Min Range: -6.0796

Max Act: 5.5482. Min Act: -0.1700

Data Index: 6488856 (Open Web Text)

Max Activating Token Index: 596