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

Dataset: Open Web Text

Neuron 169 in Layer 1

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: 3.9232. Min Range: -3.9232

Max Act: 3.9232. Min Act: -0.1700

Data Index: 3024449 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8744. Min Act: -0.1700

Data Index: 8443455 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8464. Min Act: -0.1700

Data Index: 2597108 (Open Web Text)

Max Activating Token Index: 707

Text #3

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8014. Min Act: -0.1700

Data Index: 4228874 (Open Web Text)

Max Activating Token Index: 828

Text #4

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8265. Min Act: -0.1700

Data Index: 3319980 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8258. Min Act: -0.1700

Data Index: 8572493 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8041. Min Act: -0.1700

Data Index: 6159825 (Open Web Text)

Max Activating Token Index: 49

Text #7

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7753. Min Act: -0.1700

Data Index: 8602608 (Open Web Text)

Max Activating Token Index: 161

Text #8

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7751. Min Act: -0.1700

Data Index: 6302959 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7778. Min Act: -0.1700

Data Index: 987785 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7816. Min Act: -0.1700

Data Index: 7811919 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7506. Min Act: -0.1700

Data Index: 2944697 (Open Web Text)

Max Activating Token Index: 725

Text #12

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7805. Min Act: -0.1700

Data Index: 1018764 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7155. Min Act: -0.1700

Data Index: 8387140 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7122. Min Act: -0.1700

Data Index: 1391539 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7147. Min Act: -0.1700

Data Index: 4408308 (Open Web Text)

Max Activating Token Index: 637

Text #16

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.6877. Min Act: -0.1700

Data Index: 528712 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7120. Min Act: -0.1700

Data Index: 4524018 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.6959. Min Act: -0.1700

Data Index: 6984245 (Open Web Text)

Max Activating Token Index: 568

Text #19

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7091. Min Act: -0.1700

Data Index: 4486651 (Open Web Text)

Max Activating Token Index: 653