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

Dataset: Open Web Text

Neuron 1828 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: 5.2096. Min Range: -5.2096

Max Act: 5.2096. Min Act: -0.1700

Data Index: 8195676 (Open Web Text)

Max Activating Token Index: 701

Text #1

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.1711. Min Act: -0.1700

Data Index: 4890510 (Open Web Text)

Max Activating Token Index: 950

Text #2

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.1392. Min Act: -0.1700

Data Index: 5223757 (Open Web Text)

Max Activating Token Index: 301

Text #3

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.1288. Min Act: -0.1700

Data Index: 3990676 (Open Web Text)

Max Activating Token Index: 826

Text #4

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.1032. Min Act: -0.1700

Data Index: 6927752 (Open Web Text)

Max Activating Token Index: 981

Text #5

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0904. Min Act: -0.1700

Data Index: 815794 (Open Web Text)

Max Activating Token Index: 639

Text #6

Max Range: 5.2096. Min Range: -5.2096

Max Act: 4.9858. Min Act: -0.1700

Data Index: 3987273 (Open Web Text)

Max Activating Token Index: 656

Text #7

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0410. Min Act: -0.1700

Data Index: 6235744 (Open Web Text)

Max Activating Token Index: 804

Text #8

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0417. Min Act: -0.1700

Data Index: 5011591 (Open Web Text)

Max Activating Token Index: 800

Text #9

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0238. Min Act: -0.1700

Data Index: 3693435 (Open Web Text)

Max Activating Token Index: 876

Text #10

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0330. Min Act: -0.1700

Data Index: 7498726 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0275. Min Act: -0.1700

Data Index: 5538798 (Open Web Text)

Max Activating Token Index: 542

Text #12

Max Range: 5.2096. Min Range: -5.2096

Max Act: 4.9886. Min Act: -0.1700

Data Index: 7506228 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 5.2096. Min Range: -5.2096

Max Act: 4.9838. Min Act: -0.1700

Data Index: 2173378 (Open Web Text)

Max Activating Token Index: 215

Text #14

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0006. Min Act: -0.1700

Data Index: 8223867 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0077. Min Act: -0.1700

Data Index: 3845841 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 5.2096. Min Range: -5.2096

Max Act: 4.9826. Min Act: -0.1700

Data Index: 4633910 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 5.2096. Min Range: -5.2096

Max Act: 5.0212. Min Act: -0.1700

Data Index: 5186806 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 5.2096. Min Range: -5.2096

Max Act: 4.9902. Min Act: -0.1700

Data Index: 2662119 (Open Web Text)

Max Activating Token Index: 294

Text #19

Max Range: 5.2096. Min Range: -5.2096

Max Act: 4.9991. Min Act: -0.1700

Data Index: 7469714 (Open Web Text)

Max Activating Token Index: 729