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

Dataset: Open Web Text

Neuron 1099 in Layer 0

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: 3.0281. Min Range: -3.0281

Max Act: 3.0281. Min Act: -0.1700

Data Index: 5802521 (Open Web Text)

Max Activating Token Index: 363

Text #1

Max Range: 3.0281. Min Range: -3.0281

Max Act: 3.0012. Min Act: -0.1700

Data Index: 3577389 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8778. Min Act: -0.1700

Data Index: 3992283 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8716. Min Act: -0.1700

Data Index: 6732092 (Open Web Text)

Max Activating Token Index: 174

Text #4

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8596. Min Act: -0.1700

Data Index: 7265709 (Open Web Text)

Max Activating Token Index: 945

Text #5

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8746. Min Act: -0.1700

Data Index: 983412 (Open Web Text)

Max Activating Token Index: 178

Text #6

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8517. Min Act: -0.1700

Data Index: 2229214 (Open Web Text)

Max Activating Token Index: 493

Text #7

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8587. Min Act: -0.1700

Data Index: 3090091 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8304. Min Act: -0.1700

Data Index: 4404999 (Open Web Text)

Max Activating Token Index: 918

Text #9

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8391. Min Act: -0.1700

Data Index: 3957757 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8151. Min Act: -0.1700

Data Index: 1793240 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8293. Min Act: -0.1700

Data Index: 863250 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8122. Min Act: -0.1700

Data Index: 2009823 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.8010. Min Act: -0.1700

Data Index: 831173 (Open Web Text)

Max Activating Token Index: 316

Text #14

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.7908. Min Act: -0.1700

Data Index: 420387 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.7891. Min Act: -0.1700

Data Index: 6032545 (Open Web Text)

Max Activating Token Index: 496

Text #16

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.7850. Min Act: -0.1700

Data Index: 7685725 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.7741. Min Act: -0.1700

Data Index: 4999832 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.7704. Min Act: -0.1700

Data Index: 1986395 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.0281. Min Range: -3.0281

Max Act: 2.7627. Min Act: -0.1700

Data Index: 2570900 (Open Web Text)

Max Activating Token Index: 2