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

Dataset: Open Web Text

Neuron 1926 in Layer 2

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: 4.8611. Min Range: -4.8611

Max Act: 4.8611. Min Act: -0.1700

Data Index: 1386333 (Open Web Text)

Max Activating Token Index: 180

Text #1

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7417. Min Act: -0.1700

Data Index: 426264 (Open Web Text)

Max Activating Token Index: 76

Text #2

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7335. Min Act: -0.1700

Data Index: 7899864 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7632. Min Act: -0.1700

Data Index: 6873507 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7430. Min Act: -0.1700

Data Index: 3554534 (Open Web Text)

Max Activating Token Index: 269

Text #5

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7262. Min Act: -0.1700

Data Index: 7506722 (Open Web Text)

Max Activating Token Index: 799

Text #6

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7213. Min Act: -0.1700

Data Index: 2091752 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7332. Min Act: -0.1700

Data Index: 4572249 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7014. Min Act: -0.1700

Data Index: 537834 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7338. Min Act: -0.1700

Data Index: 5034479 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7364. Min Act: -0.1700

Data Index: 5091028 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7239. Min Act: -0.1700

Data Index: 5824891 (Open Web Text)

Max Activating Token Index: 152

Text #12

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.6866. Min Act: -0.1700

Data Index: 5933515 (Open Web Text)

Max Activating Token Index: 802

Text #13

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.6884. Min Act: -0.1700

Data Index: 3632376 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.6744. Min Act: -0.1700

Data Index: 5606113 (Open Web Text)

Max Activating Token Index: 930

Text #15

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.6908. Min Act: -0.1700

Data Index: 3249732 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.7083. Min Act: -0.1700

Data Index: 4758808 (Open Web Text)

Max Activating Token Index: 735

Text #17

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.6895. Min Act: -0.1700

Data Index: 295194 (Open Web Text)

Max Activating Token Index: 850

Text #18

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.6722. Min Act: -0.1700

Data Index: 4443107 (Open Web Text)

Max Activating Token Index: 422

Text #19

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.6951. Min Act: -0.1700

Data Index: 3644617 (Open Web Text)

Max Activating Token Index: 330