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

Dataset: Open Web Text

Neuron 2232 in Layer 5

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: 4.1803. Min Range: -4.1803

Max Act: 4.1803. Min Act: -0.1700

Data Index: 7889792 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.1422. Min Act: -0.1700

Data Index: 3526914 (Open Web Text)

Max Activating Token Index: 988

Text #2

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0690. Min Act: -0.1700

Data Index: 6810522 (Open Web Text)

Max Activating Token Index: 939

Text #3

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0536. Min Act: -0.1700

Data Index: 1432292 (Open Web Text)

Max Activating Token Index: 914

Text #4

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0427. Min Act: -0.1700

Data Index: 2718593 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0597. Min Act: -0.1700

Data Index: 2512450 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0485. Min Act: -0.1700

Data Index: 5954522 (Open Web Text)

Max Activating Token Index: 886

Text #7

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0374. Min Act: -0.1700

Data Index: 3457735 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0513. Min Act: -0.1700

Data Index: 5814887 (Open Web Text)

Max Activating Token Index: 474

Text #9

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0288. Min Act: -0.1700

Data Index: 857042 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.9833. Min Act: -0.1700

Data Index: 1869093 (Open Web Text)

Max Activating Token Index: 675

Text #11

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0558. Min Act: -0.1700

Data Index: 1738164 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0586. Min Act: -0.1700

Data Index: 4892568 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.9923. Min Act: -0.1700

Data Index: 568335 (Open Web Text)

Max Activating Token Index: 775

Text #14

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0449. Min Act: -0.1700

Data Index: 3193721 (Open Web Text)

Max Activating Token Index: 817

Text #15

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0111. Min Act: -0.1700

Data Index: 2001072 (Open Web Text)

Max Activating Token Index: 537

Text #16

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.9862. Min Act: -0.1700

Data Index: 6757341 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.9777. Min Act: -0.1700

Data Index: 2334853 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.9791. Min Act: -0.1700

Data Index: 2668845 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.0012. Min Act: -0.1700

Data Index: 6322124 (Open Web Text)

Max Activating Token Index: 10