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

Dataset: Open Web Text

Neuron 1573 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: 4.9654. Min Range: -4.9654

Max Act: 4.9604. Min Act: -0.1700

Data Index: 5143587 (Open Web Text)

Max Activating Token Index: 830

Text #1

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.9654. Min Act: -0.1700

Data Index: 4017268 (Open Web Text)

Max Activating Token Index: 188

Text #2

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.9238. Min Act: -0.1700

Data Index: 2289529 (Open Web Text)

Max Activating Token Index: 337

Text #3

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.9056. Min Act: -0.1700

Data Index: 5225253 (Open Web Text)

Max Activating Token Index: 650

Text #4

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.9402. Min Act: -0.1700

Data Index: 5259693 (Open Web Text)

Max Activating Token Index: 462

Text #5

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8814. Min Act: -0.1700

Data Index: 772973 (Open Web Text)

Max Activating Token Index: 526

Text #6

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8930. Min Act: -0.1700

Data Index: 7803627 (Open Web Text)

Max Activating Token Index: 823

Text #7

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8760. Min Act: -0.1700

Data Index: 8666636 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8571. Min Act: -0.1700

Data Index: 8266402 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8482. Min Act: -0.1700

Data Index: 6528893 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8700. Min Act: -0.1700

Data Index: 5322082 (Open Web Text)

Max Activating Token Index: 281

Text #11

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8484. Min Act: -0.1700

Data Index: 7754593 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8218. Min Act: -0.1700

Data Index: 668149 (Open Web Text)

Max Activating Token Index: 418

Text #13

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8354. Min Act: -0.1700

Data Index: 5417526 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8344. Min Act: -0.1700

Data Index: 3714764 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8361. Min Act: -0.1700

Data Index: 7181583 (Open Web Text)

Max Activating Token Index: 255

Text #16

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8223. Min Act: -0.1700

Data Index: 7385446 (Open Web Text)

Max Activating Token Index: 644

Text #17

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8273. Min Act: -0.1700

Data Index: 1456999 (Open Web Text)

Max Activating Token Index: 866

Text #18

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8005. Min Act: -0.1700

Data Index: 6576901 (Open Web Text)

Max Activating Token Index: 215

Text #19

Max Range: 4.9654. Min Range: -4.9654

Max Act: 4.8126. Min Act: -0.1700

Data Index: 7410902 (Open Web Text)

Max Activating Token Index: 308