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

Dataset: Open Web Text

Neuron 949 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: 5.9868. Min Range: -5.9868

Max Act: 5.9868. Min Act: -0.1700

Data Index: 7515061 (Open Web Text)

Max Activating Token Index: 471

Text #1

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.9526. Min Act: -0.1700

Data Index: 6616983 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.9406. Min Act: -0.1700

Data Index: 4315699 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8394. Min Act: -0.1700

Data Index: 4368456 (Open Web Text)

Max Activating Token Index: 279

Text #4

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8605. Min Act: -0.1700

Data Index: 586698 (Open Web Text)

Max Activating Token Index: 183

Text #5

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8778. Min Act: -0.1700

Data Index: 472478 (Open Web Text)

Max Activating Token Index: 902

Text #6

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8835. Min Act: -0.1700

Data Index: 7449491 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8814. Min Act: -0.1700

Data Index: 3803653 (Open Web Text)

Max Activating Token Index: 838

Text #8

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8877. Min Act: -0.1700

Data Index: 7812537 (Open Web Text)

Max Activating Token Index: 444

Text #9

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.7990. Min Act: -0.1700

Data Index: 8806253 (Open Web Text)

Max Activating Token Index: 974

Text #10

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8600. Min Act: -0.1700

Data Index: 154586 (Open Web Text)

Max Activating Token Index: 956

Text #11

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.7739. Min Act: -0.1700

Data Index: 4988480 (Open Web Text)

Max Activating Token Index: 514

Text #12

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.7904. Min Act: -0.1700

Data Index: 224049 (Open Web Text)

Max Activating Token Index: 902

Text #13

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.7640. Min Act: -0.1700

Data Index: 3611078 (Open Web Text)

Max Activating Token Index: 480

Text #14

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8024. Min Act: -0.1700

Data Index: 3905629 (Open Web Text)

Max Activating Token Index: 89

Text #15

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8122. Min Act: -0.1700

Data Index: 11038 (Open Web Text)

Max Activating Token Index: 133

Text #16

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.7622. Min Act: -0.1700

Data Index: 8385636 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.8256. Min Act: -0.1700

Data Index: 8337147 (Open Web Text)

Max Activating Token Index: 607

Text #18

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.7431. Min Act: -0.1700

Data Index: 5743763 (Open Web Text)

Max Activating Token Index: 266

Text #19

Max Range: 5.9868. Min Range: -5.9868

Max Act: 5.7977. Min Act: -0.1700

Data Index: 1090082 (Open Web Text)

Max Activating Token Index: 188