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

Dataset: Open Web Text

Neuron 2561 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: 5.3420. Min Range: -5.3420

Max Act: 5.3420. Min Act: -0.1700

Data Index: 5283437 (Open Web Text)

Max Activating Token Index: 781

Text #1

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.1685. Min Act: -0.1700

Data Index: 7406673 (Open Web Text)

Max Activating Token Index: 1009

Text #2

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.1796. Min Act: -0.1700

Data Index: 3744440 (Open Web Text)

Max Activating Token Index: 747

Text #3

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.0905. Min Act: -0.1700

Data Index: 3072085 (Open Web Text)

Max Activating Token Index: 764

Text #4

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.1081. Min Act: -0.1700

Data Index: 2214289 (Open Web Text)

Max Activating Token Index: 734

Text #5

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.0707. Min Act: -0.1700

Data Index: 3852262 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.0732. Min Act: -0.1700

Data Index: 1764819 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.0501. Min Act: -0.1700

Data Index: 2201504 (Open Web Text)

Max Activating Token Index: 980

Text #8

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.0260. Min Act: -0.1700

Data Index: 5058717 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 5.3420. Min Range: -5.3420

Max Act: 5.0212. Min Act: -0.1700

Data Index: 5703619 (Open Web Text)

Max Activating Token Index: 600

Text #10

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.9370. Min Act: -0.1700

Data Index: 2829487 (Open Web Text)

Max Activating Token Index: 949

Text #11

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.9429. Min Act: -0.1700

Data Index: 4291109 (Open Web Text)

Max Activating Token Index: 232

Text #12

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.9267. Min Act: -0.1700

Data Index: 3712253 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.9469. Min Act: -0.1700

Data Index: 8387413 (Open Web Text)

Max Activating Token Index: 368

Text #14

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.9475. Min Act: -0.1700

Data Index: 8298522 (Open Web Text)

Max Activating Token Index: 807

Text #15

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.9045. Min Act: -0.1700

Data Index: 6710812 (Open Web Text)

Max Activating Token Index: 482

Text #16

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.9170. Min Act: -0.1700

Data Index: 927903 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.8790. Min Act: -0.1700

Data Index: 7076587 (Open Web Text)

Max Activating Token Index: 243

Text #18

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.8748. Min Act: -0.1700

Data Index: 5058716 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 5.3420. Min Range: -5.3420

Max Act: 4.8718. Min Act: -0.1700

Data Index: 6460867 (Open Web Text)

Max Activating Token Index: 688