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

Dataset: Open Web Text

Neuron 331 in Layer 3

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: 4.0758. Min Range: -4.0758

Max Act: 4.0731. Min Act: -0.1700

Data Index: 874001 (Open Web Text)

Max Activating Token Index: 69

Text #1

Max Range: 4.0758. Min Range: -4.0758

Max Act: 4.0557. Min Act: -0.1700

Data Index: 5514294 (Open Web Text)

Max Activating Token Index: 961

Text #2

Max Range: 4.0758. Min Range: -4.0758

Max Act: 4.0693. Min Act: -0.1700

Data Index: 3864265 (Open Web Text)

Max Activating Token Index: 619

Text #3

Max Range: 4.0758. Min Range: -4.0758

Max Act: 4.0758. Min Act: -0.1700

Data Index: 3221001 (Open Web Text)

Max Activating Token Index: 736

Text #4

Max Range: 4.0758. Min Range: -4.0758

Max Act: 4.0190. Min Act: -0.1700

Data Index: 5514299 (Open Web Text)

Max Activating Token Index: 185

Text #5

Max Range: 4.0758. Min Range: -4.0758

Max Act: 4.0037. Min Act: -0.1700

Data Index: 2999061 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9818. Min Act: -0.1700

Data Index: 2622519 (Open Web Text)

Max Activating Token Index: 1011

Text #7

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9695. Min Act: -0.1700

Data Index: 1110912 (Open Web Text)

Max Activating Token Index: 954

Text #8

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9504. Min Act: -0.1700

Data Index: 5520927 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9614. Min Act: -0.1700

Data Index: 4613761 (Open Web Text)

Max Activating Token Index: 564

Text #10

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9407. Min Act: -0.1700

Data Index: 1954921 (Open Web Text)

Max Activating Token Index: 774

Text #11

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9257. Min Act: -0.1700

Data Index: 2538627 (Open Web Text)

Max Activating Token Index: 905

Text #12

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9447. Min Act: -0.1700

Data Index: 2510239 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9338. Min Act: -0.1700

Data Index: 3190479 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9027. Min Act: -0.1700

Data Index: 1803796 (Open Web Text)

Max Activating Token Index: 877

Text #15

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9077. Min Act: -0.1700

Data Index: 4490012 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9359. Min Act: -0.1700

Data Index: 939272 (Open Web Text)

Max Activating Token Index: 969

Text #17

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9386. Min Act: -0.1700

Data Index: 4856670 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9240. Min Act: -0.1700

Data Index: 6368039 (Open Web Text)

Max Activating Token Index: 384

Text #19

Max Range: 4.0758. Min Range: -4.0758

Max Act: 3.9029. Min Act: -0.1700

Data Index: 2254451 (Open Web Text)

Max Activating Token Index: 906