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

Dataset: Open Web Text

Neuron 650 in Layer 6

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: 5.7908. Min Range: -5.7908

Max Act: 5.7908. Min Act: -0.1700

Data Index: 2629725 (Open Web Text)

Max Activating Token Index: 543

Text #1

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.7647. Min Act: -0.1700

Data Index: 7793228 (Open Web Text)

Max Activating Token Index: 403

Text #2

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.7083. Min Act: -0.1700

Data Index: 5591696 (Open Web Text)

Max Activating Token Index: 316

Text #3

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.6644. Min Act: -0.1700

Data Index: 1517935 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.6445. Min Act: -0.1700

Data Index: 6878521 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.5119. Min Act: -0.1700

Data Index: 4420275 (Open Web Text)

Max Activating Token Index: 714

Text #6

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4779. Min Act: -0.1700

Data Index: 7915277 (Open Web Text)

Max Activating Token Index: 152

Text #7

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4917. Min Act: -0.1700

Data Index: 3153421 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4993. Min Act: -0.1700

Data Index: 1810372 (Open Web Text)

Max Activating Token Index: 247

Text #9

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4526. Min Act: -0.1700

Data Index: 3939634 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4635. Min Act: -0.1700

Data Index: 4033282 (Open Web Text)

Max Activating Token Index: 879

Text #11

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4635. Min Act: -0.1700

Data Index: 2815050 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4048. Min Act: -0.1700

Data Index: 2794226 (Open Web Text)

Max Activating Token Index: 638

Text #13

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4282. Min Act: -0.1700

Data Index: 5205584 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4223. Min Act: -0.1700

Data Index: 4612674 (Open Web Text)

Max Activating Token Index: 891

Text #15

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4284. Min Act: -0.1700

Data Index: 3119425 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.3616. Min Act: -0.1700

Data Index: 6475661 (Open Web Text)

Max Activating Token Index: 911

Text #17

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4552. Min Act: -0.1700

Data Index: 5079634 (Open Web Text)

Max Activating Token Index: 970

Text #18

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.3846. Min Act: -0.1700

Data Index: 810453 (Open Web Text)

Max Activating Token Index: 744

Text #19

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.4187. Min Act: -0.1700

Data Index: 1607459 (Open Web Text)

Max Activating Token Index: 803