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

Dataset: Open Web Text

Neuron 500 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: 1.9797. Min Range: -1.9797

Max Act: 1.9797. Min Act: -0.1700

Data Index: 4600486 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.9165. Min Act: -0.1700

Data Index: 6692508 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.9218. Min Act: -0.1700

Data Index: 4752813 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.9129. Min Act: -0.1700

Data Index: 2690960 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8982. Min Act: -0.1700

Data Index: 7971723 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8772. Min Act: -0.1700

Data Index: 5643837 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8790. Min Act: -0.1700

Data Index: 7304681 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8793. Min Act: -0.1700

Data Index: 5637690 (Open Web Text)

Max Activating Token Index: 845

Text #8

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8771. Min Act: -0.1700

Data Index: 8354800 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8799. Min Act: -0.1700

Data Index: 3814471 (Open Web Text)

Max Activating Token Index: 66

Text #10

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8636. Min Act: -0.1700

Data Index: 8046824 (Open Web Text)

Max Activating Token Index: 278

Text #11

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8627. Min Act: -0.1700

Data Index: 4576790 (Open Web Text)

Max Activating Token Index: 729

Text #12

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8621. Min Act: -0.1700

Data Index: 5002366 (Open Web Text)

Max Activating Token Index: 71

Text #13

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8655. Min Act: -0.1698

Data Index: 619755 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8696. Min Act: -0.1700

Data Index: 842777 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8615. Min Act: -0.1700

Data Index: 8591565 (Open Web Text)

Max Activating Token Index: 118

Text #16

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8639. Min Act: -0.1700

Data Index: 7046819 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8611. Min Act: -0.1700

Data Index: 17152 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8602. Min Act: -0.1700

Data Index: 4877048 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 1.9797. Min Range: -1.9797

Max Act: 1.8631. Min Act: -0.1700

Data Index: 1802137 (Open Web Text)

Max Activating Token Index: 71