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

Dataset: Open Web Text

Neuron 812 in Layer 6

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: 3.2300. Min Range: -3.2300

Max Act: 3.2300. Min Act: -0.1700

Data Index: 8250308 (Open Web Text)

Max Activating Token Index: 248

Text #1

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.1865. Min Act: -0.1700

Data Index: 8278460 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.1556. Min Act: -0.1700

Data Index: 7180877 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.1381. Min Act: -0.1700

Data Index: 2967376 (Open Web Text)

Max Activating Token Index: 374

Text #4

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0792. Min Act: -0.1700

Data Index: 2229315 (Open Web Text)

Max Activating Token Index: 827

Text #5

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0685. Min Act: -0.1700

Data Index: 8259722 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0891. Min Act: -0.1700

Data Index: 5074827 (Open Web Text)

Max Activating Token Index: 317

Text #7

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0454. Min Act: -0.1700

Data Index: 3015900 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0622. Min Act: -0.1700

Data Index: 7216306 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0055. Min Act: -0.1700

Data Index: 5257004 (Open Web Text)

Max Activating Token Index: 319

Text #10

Max Range: 3.2300. Min Range: -3.2300

Max Act: 2.9781. Min Act: -0.1700

Data Index: 2785005 (Open Web Text)

Max Activating Token Index: 737

Text #11

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0264. Min Act: -0.1700

Data Index: 3004391 (Open Web Text)

Max Activating Token Index: 203

Text #12

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0310. Min Act: -0.1700

Data Index: 5497575 (Open Web Text)

Max Activating Token Index: 415

Text #13

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0167. Min Act: -0.1700

Data Index: 4830146 (Open Web Text)

Max Activating Token Index: 938

Text #14

Max Range: 3.2300. Min Range: -3.2300

Max Act: 3.0054. Min Act: -0.1700

Data Index: 1891656 (Open Web Text)

Max Activating Token Index: 116

Text #15

Max Range: 3.2300. Min Range: -3.2300

Max Act: 2.9863. Min Act: -0.1700

Data Index: 7695358 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 3.2300. Min Range: -3.2300

Max Act: 2.9848. Min Act: -0.1700

Data Index: 366583 (Open Web Text)

Max Activating Token Index: 982

Text #17

Max Range: 3.2300. Min Range: -3.2300

Max Act: 2.9603. Min Act: -0.1700

Data Index: 997771 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 3.2300. Min Range: -3.2300

Max Act: 2.9695. Min Act: -0.1700

Data Index: 3087634 (Open Web Text)

Max Activating Token Index: 617

Text #19

Max Range: 3.2300. Min Range: -3.2300

Max Act: 2.9693. Min Act: -0.1700

Data Index: 7087215 (Open Web Text)

Max Activating Token Index: 349