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

Dataset: Open Web Text

Neuron 413 in Layer 5

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: 4.0945. Min Range: -4.0945

Max Act: 4.0891. Min Act: -0.1700

Data Index: 8460895 (Open Web Text)

Max Activating Token Index: 924

Text #1

Max Range: 4.0945. Min Range: -4.0945

Max Act: 4.0945. Min Act: -0.1700

Data Index: 3452210 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 4.0945. Min Range: -4.0945

Max Act: 4.0520. Min Act: -0.1700

Data Index: 7539549 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 4.0945. Min Range: -4.0945

Max Act: 4.0769. Min Act: -0.1700

Data Index: 4745864 (Open Web Text)

Max Activating Token Index: 934

Text #4

Max Range: 4.0945. Min Range: -4.0945

Max Act: 4.0412. Min Act: -0.1700

Data Index: 6596357 (Open Web Text)

Max Activating Token Index: 148

Text #5

Max Range: 4.0945. Min Range: -4.0945

Max Act: 4.0335. Min Act: -0.1700

Data Index: 4390387 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 4.0945. Min Range: -4.0945

Max Act: 4.0551. Min Act: -0.1700

Data Index: 4619434 (Open Web Text)

Max Activating Token Index: 120

Text #7

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9758. Min Act: -0.1700

Data Index: 3318731 (Open Web Text)

Max Activating Token Index: 499

Text #8

Max Range: 4.0945. Min Range: -4.0945

Max Act: 4.0368. Min Act: -0.1700

Data Index: 6731258 (Open Web Text)

Max Activating Token Index: 724

Text #9

Max Range: 4.0945. Min Range: -4.0945

Max Act: 4.0525. Min Act: -0.1700

Data Index: 1819771 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9917. Min Act: -0.1700

Data Index: 4956423 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9786. Min Act: -0.1700

Data Index: 4853494 (Open Web Text)

Max Activating Token Index: 499

Text #12

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9583. Min Act: -0.1700

Data Index: 1717544 (Open Web Text)

Max Activating Token Index: 632

Text #13

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9832. Min Act: -0.1700

Data Index: 3865293 (Open Web Text)

Max Activating Token Index: 222

Text #14

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9441. Min Act: -0.1700

Data Index: 1203960 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9348. Min Act: -0.1700

Data Index: 4976512 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9211. Min Act: -0.1700

Data Index: 1523785 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9113. Min Act: -0.1700

Data Index: 806703 (Open Web Text)

Max Activating Token Index: 1014

Text #18

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.9164. Min Act: -0.1700

Data Index: 6618357 (Open Web Text)

Max Activating Token Index: 515

Text #19

Max Range: 4.0945. Min Range: -4.0945

Max Act: 3.8983. Min Act: -0.1700

Data Index: 4824744 (Open Web Text)

Max Activating Token Index: 905