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

Dataset: Open Web Text

Neuron 1662 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: 1.7084. Min Range: -1.7084

Max Act: 1.7058. Min Act: -0.1700

Data Index: 507738 (Open Web Text)

Max Activating Token Index: 247

Text #1

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.7084. Min Act: -0.1700

Data Index: 3046133 (Open Web Text)

Max Activating Token Index: 167

Text #2

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.7047. Min Act: -0.1700

Data Index: 4628730 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6985. Min Act: -0.1700

Data Index: 4052778 (Open Web Text)

Max Activating Token Index: 997

Text #4

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6991. Min Act: -0.1700

Data Index: 1697807 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6861. Min Act: -0.1700

Data Index: 8304314 (Open Web Text)

Max Activating Token Index: 335

Text #6

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6704. Min Act: -0.1700

Data Index: 7978662 (Open Web Text)

Max Activating Token Index: 970

Text #7

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6889. Min Act: -0.1700

Data Index: 803541 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6826. Min Act: -0.1700

Data Index: 7016843 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6675. Min Act: -0.1700

Data Index: 1124981 (Open Web Text)

Max Activating Token Index: 430

Text #10

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6689. Min Act: -0.1700

Data Index: 8734776 (Open Web Text)

Max Activating Token Index: 753

Text #11

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6645. Min Act: -0.1700

Data Index: 5432470 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6588. Min Act: -0.1700

Data Index: 7656554 (Open Web Text)

Max Activating Token Index: 67

Text #13

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6527. Min Act: -0.1700

Data Index: 8442233 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6590. Min Act: -0.1700

Data Index: 3898472 (Open Web Text)

Max Activating Token Index: 525

Text #15

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6429. Min Act: -0.1700

Data Index: 1559100 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6357. Min Act: -0.1700

Data Index: 2537603 (Open Web Text)

Max Activating Token Index: 95

Text #17

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6470. Min Act: -0.1700

Data Index: 609316 (Open Web Text)

Max Activating Token Index: 374

Text #18

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6457. Min Act: -0.1700

Data Index: 4544119 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 1.7084. Min Range: -1.7084

Max Act: 1.6455. Min Act: -0.1700

Data Index: 4354563 (Open Web Text)

Max Activating Token Index: 159