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

Dataset: Open Web Text

Neuron 2737 in Layer 1

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: 3.7793. Min Range: -3.7793

Max Act: 3.7793. Min Act: -0.1700

Data Index: 2331787 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.7009. Min Act: -0.1700

Data Index: 4875176 (Open Web Text)

Max Activating Token Index: 422

Text #2

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6820. Min Act: -0.1700

Data Index: 2493432 (Open Web Text)

Max Activating Token Index: 690

Text #3

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6938. Min Act: -0.1700

Data Index: 4276680 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6718. Min Act: -0.1700

Data Index: 801765 (Open Web Text)

Max Activating Token Index: 604

Text #5

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6918. Min Act: -0.1700

Data Index: 2754059 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6633. Min Act: -0.1700

Data Index: 5937581 (Open Web Text)

Max Activating Token Index: 665

Text #7

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6635. Min Act: -0.1700

Data Index: 8031388 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6529. Min Act: -0.1700

Data Index: 2253107 (Open Web Text)

Max Activating Token Index: 551

Text #9

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6386. Min Act: -0.1700

Data Index: 3917188 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6514. Min Act: -0.1700

Data Index: 3874584 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6661. Min Act: -0.1700

Data Index: 457494 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6634. Min Act: -0.1700

Data Index: 8342004 (Open Web Text)

Max Activating Token Index: 767

Text #13

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6279. Min Act: -0.1700

Data Index: 6328722 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6280. Min Act: -0.1700

Data Index: 4428395 (Open Web Text)

Max Activating Token Index: 515

Text #15

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6313. Min Act: -0.1700

Data Index: 630183 (Open Web Text)

Max Activating Token Index: 712

Text #16

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6213. Min Act: -0.1700

Data Index: 4345664 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.5868. Min Act: -0.1700

Data Index: 2310196 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6089. Min Act: -0.1700

Data Index: 4337352 (Open Web Text)

Max Activating Token Index: 475

Text #19

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6220. Min Act: -0.1700

Data Index: 1346817 (Open Web Text)

Max Activating Token Index: 458