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

Dataset: Open Web Text

Neuron 464 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: 7.1447. Min Range: -7.1447

Max Act: 7.1447. Min Act: -0.1700

Data Index: 4819685 (Open Web Text)

Max Activating Token Index: 240

Text #1

Max Range: 7.1447. Min Range: -7.1447

Max Act: 7.0416. Min Act: -0.1700

Data Index: 3559035 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 7.1447. Min Range: -7.1447

Max Act: 7.0571. Min Act: -0.1700

Data Index: 5273902 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.9848. Min Act: -0.1700

Data Index: 1752710 (Open Web Text)

Max Activating Token Index: 791

Text #4

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.8847. Min Act: -0.1700

Data Index: 5749150 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.8530. Min Act: -0.1700

Data Index: 1680898 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.8153. Min Act: -0.1700

Data Index: 2919584 (Open Web Text)

Max Activating Token Index: 991

Text #7

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.7910. Min Act: -0.1700

Data Index: 3264486 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.8137. Min Act: -0.1700

Data Index: 3435739 (Open Web Text)

Max Activating Token Index: 460

Text #9

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.7708. Min Act: -0.1700

Data Index: 219517 (Open Web Text)

Max Activating Token Index: 946

Text #10

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.7429. Min Act: -0.1700

Data Index: 4673640 (Open Web Text)

Max Activating Token Index: 200

Text #11

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.7826. Min Act: -0.1700

Data Index: 7730699 (Open Web Text)

Max Activating Token Index: 164

Text #12

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.7394. Min Act: -0.1700

Data Index: 7330070 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.7471. Min Act: -0.1700

Data Index: 1680896 (Open Web Text)

Max Activating Token Index: 95

Text #14

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.7139. Min Act: -0.1700

Data Index: 1680895 (Open Web Text)

Max Activating Token Index: 49

Text #15

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.6827. Min Act: -0.1700

Data Index: 6659009 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.6979. Min Act: -0.1700

Data Index: 6241772 (Open Web Text)

Max Activating Token Index: 27

Text #17

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.6961. Min Act: -0.1700

Data Index: 4157861 (Open Web Text)

Max Activating Token Index: 769

Text #18

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.6543. Min Act: -0.1700

Data Index: 451754 (Open Web Text)

Max Activating Token Index: 77

Text #19

Max Range: 7.1447. Min Range: -7.1447

Max Act: 6.6000. Min Act: -0.1700

Data Index: 2799411 (Open Web Text)

Max Activating Token Index: 525