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

Dataset: Open Web Text

Neuron 2847 in Layer 2

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: 2.2611. Min Range: -2.2611

Max Act: 2.2611. Min Act: -0.1700

Data Index: 6944737 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.2256. Min Act: -0.1700

Data Index: 6697132 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.2276. Min Act: -0.1700

Data Index: 1997005 (Open Web Text)

Max Activating Token Index: 801

Text #3

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.2242. Min Act: -0.1700

Data Index: 2664109 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.2120. Min Act: -0.1700

Data Index: 1764117 (Open Web Text)

Max Activating Token Index: 970

Text #5

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.2267. Min Act: -0.1700

Data Index: 8479450 (Open Web Text)

Max Activating Token Index: 314

Text #6

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1917. Min Act: -0.1700

Data Index: 4143644 (Open Web Text)

Max Activating Token Index: 660

Text #7

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1885. Min Act: -0.1700

Data Index: 4257223 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1902. Min Act: -0.1700

Data Index: 4549112 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1811. Min Act: -0.1700

Data Index: 2988184 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1588. Min Act: -0.1700

Data Index: 150981 (Open Web Text)

Max Activating Token Index: 860

Text #11

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1666. Min Act: -0.1700

Data Index: 6626593 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1771. Min Act: -0.1700

Data Index: 1200930 (Open Web Text)

Max Activating Token Index: 464

Text #13

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1578. Min Act: -0.1700

Data Index: 5019481 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1863. Min Act: -0.1700

Data Index: 2865710 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1775. Min Act: -0.1700

Data Index: 6803249 (Open Web Text)

Max Activating Token Index: 270

Text #16

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1765. Min Act: -0.1700

Data Index: 3791381 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1650. Min Act: -0.1700

Data Index: 5540749 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1580. Min Act: -0.1700

Data Index: 1504278 (Open Web Text)

Max Activating Token Index: 939

Text #19

Max Range: 2.2611. Min Range: -2.2611

Max Act: 2.1374. Min Act: -0.1700

Data Index: 691947 (Open Web Text)

Max Activating Token Index: 761