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

Dataset: Open Web Text

Neuron 629 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: 3.8603. Min Range: -3.8603

Max Act: 3.8603. Min Act: -0.1700

Data Index: 1854843 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.7348. Min Act: -0.1700

Data Index: 3721975 (Open Web Text)

Max Activating Token Index: 883

Text #2

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.7288. Min Act: -0.1700

Data Index: 8771817 (Open Web Text)

Max Activating Token Index: 247

Text #3

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.7042. Min Act: -0.1700

Data Index: 764690 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6539. Min Act: -0.1700

Data Index: 7683664 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6544. Min Act: -0.1700

Data Index: 3314770 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6207. Min Act: -0.1700

Data Index: 6326826 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6254. Min Act: -0.1700

Data Index: 7944481 (Open Web Text)

Max Activating Token Index: 930

Text #8

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6263. Min Act: -0.1700

Data Index: 5339950 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6216. Min Act: -0.1700

Data Index: 4774944 (Open Web Text)

Max Activating Token Index: 665

Text #10

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6223. Min Act: -0.1700

Data Index: 7293392 (Open Web Text)

Max Activating Token Index: 365

Text #11

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6374. Min Act: -0.1700

Data Index: 8778358 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6178. Min Act: -0.1700

Data Index: 8518792 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6118. Min Act: -0.1700

Data Index: 8487483 (Open Web Text)

Max Activating Token Index: 236

Text #14

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6203. Min Act: -0.1700

Data Index: 627011 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.5952. Min Act: -0.1700

Data Index: 3645934 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.5815. Min Act: -0.1700

Data Index: 8070022 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.6072. Min Act: -0.1700

Data Index: 6132068 (Open Web Text)

Max Activating Token Index: 590

Text #18

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.5600. Min Act: -0.1700

Data Index: 4656200 (Open Web Text)

Max Activating Token Index: 274

Text #19

Max Range: 3.8603. Min Range: -3.8603

Max Act: 3.5614. Min Act: -0.1700

Data Index: 3793440 (Open Web Text)

Max Activating Token Index: 944