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

Dataset: Open Web Text

Neuron 1223 in Layer 0

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: 1.2791. Min Range: -1.2791

Max Act: 1.2769. Min Act: -0.1700

Data Index: 1818785 (Open Web Text)

Max Activating Token Index: 450

Text #1

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2791. Min Act: -0.1700

Data Index: 301213 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2677. Min Act: -0.1700

Data Index: 2321629 (Open Web Text)

Max Activating Token Index: 440

Text #3

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2593. Min Act: -0.1700

Data Index: 7083023 (Open Web Text)

Max Activating Token Index: 438

Text #4

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2516. Min Act: -0.1700

Data Index: 301221 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2498. Min Act: -0.1700

Data Index: 4565671 (Open Web Text)

Max Activating Token Index: 432

Text #6

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2495. Min Act: -0.1700

Data Index: 6622970 (Open Web Text)

Max Activating Token Index: 435

Text #7

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2457. Min Act: -0.1700

Data Index: 1980864 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2481. Min Act: -0.1700

Data Index: 5420207 (Open Web Text)

Max Activating Token Index: 443

Text #9

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2496. Min Act: -0.1700

Data Index: 1142454 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2367. Min Act: -0.1700

Data Index: 1343775 (Open Web Text)

Max Activating Token Index: 445

Text #11

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2439. Min Act: -0.1700

Data Index: 2660260 (Open Web Text)

Max Activating Token Index: 431

Text #12

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2380. Min Act: -0.1700

Data Index: 2773287 (Open Web Text)

Max Activating Token Index: 436

Text #13

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2391. Min Act: -0.1700

Data Index: 6503042 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2437. Min Act: -0.1700

Data Index: 3265747 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2372. Min Act: -0.1700

Data Index: 4438577 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2447. Min Act: -0.1700

Data Index: 4471769 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2424. Min Act: -0.1700

Data Index: 8166714 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2362. Min Act: -0.1700

Data Index: 5203828 (Open Web Text)

Max Activating Token Index: 433

Text #19

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2388. Min Act: -0.1700

Data Index: 1717693 (Open Web Text)

Max Activating Token Index: 421