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

Dataset: Open Web Text

Neuron 1290 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: 4.5836. Min Range: -4.5836

Max Act: 4.5836. Min Act: -0.1700

Data Index: 337355 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.5647. Min Act: -0.1700

Data Index: 337351 (Open Web Text)

Max Activating Token Index: 974

Text #2

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.5749. Min Act: -0.1700

Data Index: 5677598 (Open Web Text)

Max Activating Token Index: 112

Text #3

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.5469. Min Act: -0.1700

Data Index: 337352 (Open Web Text)

Max Activating Token Index: 119

Text #4

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.5081. Min Act: -0.1700

Data Index: 2951446 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4564. Min Act: -0.1700

Data Index: 6147083 (Open Web Text)

Max Activating Token Index: 653

Text #6

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4617. Min Act: -0.1700

Data Index: 3219036 (Open Web Text)

Max Activating Token Index: 583

Text #7

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4215. Min Act: -0.1700

Data Index: 5032591 (Open Web Text)

Max Activating Token Index: 783

Text #8

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4588. Min Act: -0.1700

Data Index: 3146176 (Open Web Text)

Max Activating Token Index: 795

Text #9

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4332. Min Act: -0.1700

Data Index: 4120751 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4762. Min Act: -0.1700

Data Index: 7532436 (Open Web Text)

Max Activating Token Index: 945

Text #11

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4204. Min Act: -0.1700

Data Index: 4519503 (Open Web Text)

Max Activating Token Index: 227

Text #12

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4238. Min Act: -0.1700

Data Index: 5677609 (Open Web Text)

Max Activating Token Index: 273

Text #13

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4474. Min Act: -0.1700

Data Index: 2532794 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.3856. Min Act: -0.1700

Data Index: 4274285 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.4025. Min Act: -0.1700

Data Index: 3232730 (Open Web Text)

Max Activating Token Index: 495

Text #16

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.3838. Min Act: -0.1700

Data Index: 5987573 (Open Web Text)

Max Activating Token Index: 835

Text #17

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.3744. Min Act: -0.1700

Data Index: 7203715 (Open Web Text)

Max Activating Token Index: 734

Text #18

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.3823. Min Act: -0.1700

Data Index: 3145882 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 4.5836. Min Range: -4.5836

Max Act: 4.3372. Min Act: -0.1700

Data Index: 4176726 (Open Web Text)

Max Activating Token Index: 783