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

Dataset: Open Web Text

Neuron 625 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: 5.5719. Min Range: -5.5719

Max Act: 5.5719. Min Act: -0.1700

Data Index: 889193 (Open Web Text)

Max Activating Token Index: 37

Text #1

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.5407. Min Act: -0.1700

Data Index: 5553062 (Open Web Text)

Max Activating Token Index: 322

Text #2

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.5445. Min Act: -0.1700

Data Index: 5301210 (Open Web Text)

Max Activating Token Index: 161

Text #3

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.5127. Min Act: -0.1700

Data Index: 3179619 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.5264. Min Act: -0.1700

Data Index: 5344631 (Open Web Text)

Max Activating Token Index: 646

Text #5

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.5028. Min Act: -0.1700

Data Index: 4526101 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4636. Min Act: -0.1700

Data Index: 456239 (Open Web Text)

Max Activating Token Index: 620

Text #7

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4807. Min Act: -0.1700

Data Index: 6762732 (Open Web Text)

Max Activating Token Index: 367

Text #8

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4427. Min Act: -0.1700

Data Index: 3035632 (Open Web Text)

Max Activating Token Index: 273

Text #9

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4532. Min Act: -0.1700

Data Index: 964156 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4645. Min Act: -0.1700

Data Index: 4674388 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4452. Min Act: -0.1700

Data Index: 2902095 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4592. Min Act: -0.1700

Data Index: 7361053 (Open Web Text)

Max Activating Token Index: 37

Text #13

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4502. Min Act: -0.1700

Data Index: 3238965 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4719. Min Act: -0.1700

Data Index: 2636779 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4263. Min Act: -0.1700

Data Index: 689306 (Open Web Text)

Max Activating Token Index: 997

Text #16

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4554. Min Act: -0.1700

Data Index: 4699017 (Open Web Text)

Max Activating Token Index: 575

Text #17

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4194. Min Act: -0.1700

Data Index: 4798562 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4286. Min Act: -0.1700

Data Index: 5154150 (Open Web Text)

Max Activating Token Index: 26

Text #19

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.4364. Min Act: -0.1700

Data Index: 3988090 (Open Web Text)

Max Activating Token Index: 961