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

Dataset: Open Web Text

Neuron 2699 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: 3.8850. Min Range: -3.8850

Max Act: 3.8850. Min Act: -0.1700

Data Index: 3702126 (Open Web Text)

Max Activating Token Index: 390

Text #1

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.8253. Min Act: -0.1700

Data Index: 8669916 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7982. Min Act: -0.1700

Data Index: 4310924 (Open Web Text)

Max Activating Token Index: 750

Text #3

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7218. Min Act: -0.1700

Data Index: 6692152 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7335. Min Act: -0.1700

Data Index: 7116689 (Open Web Text)

Max Activating Token Index: 155

Text #5

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7412. Min Act: -0.1700

Data Index: 276705 (Open Web Text)

Max Activating Token Index: 994

Text #6

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7527. Min Act: -0.1700

Data Index: 850109 (Open Web Text)

Max Activating Token Index: 454

Text #7

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6930. Min Act: -0.1700

Data Index: 6864037 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7131. Min Act: -0.1700

Data Index: 8224082 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6980. Min Act: -0.1700

Data Index: 8096304 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7231. Min Act: -0.1700

Data Index: 3966370 (Open Web Text)

Max Activating Token Index: 796

Text #11

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6551. Min Act: -0.1700

Data Index: 1433556 (Open Web Text)

Max Activating Token Index: 704

Text #12

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6789. Min Act: -0.1700

Data Index: 4658309 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.7006. Min Act: -0.1700

Data Index: 1480284 (Open Web Text)

Max Activating Token Index: 563

Text #14

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6305. Min Act: -0.1700

Data Index: 7396748 (Open Web Text)

Max Activating Token Index: 193

Text #15

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6338. Min Act: -0.1700

Data Index: 6573422 (Open Web Text)

Max Activating Token Index: 418

Text #16

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6301. Min Act: -0.1700

Data Index: 8335733 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6315. Min Act: -0.1700

Data Index: 8801732 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6425. Min Act: -0.1700

Data Index: 4141908 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.6220. Min Act: -0.1700

Data Index: 6384465 (Open Web Text)

Max Activating Token Index: 918