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

Dataset: Open Web Text

Neuron 2300 in Layer 6

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: 4.0583. Min Range: -4.0583

Max Act: 4.0583. Min Act: -0.1700

Data Index: 7892461 (Open Web Text)

Max Activating Token Index: 122

Text #1

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.8756. Min Act: -0.1700

Data Index: 7070855 (Open Web Text)

Max Activating Token Index: 617

Text #2

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.8497. Min Act: -0.1700

Data Index: 6926630 (Open Web Text)

Max Activating Token Index: 211

Text #3

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.8072. Min Act: -0.1700

Data Index: 4943057 (Open Web Text)

Max Activating Token Index: 837

Text #4

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.7944. Min Act: -0.1700

Data Index: 5307315 (Open Web Text)

Max Activating Token Index: 212

Text #5

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.8069. Min Act: -0.1700

Data Index: 4464328 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.7775. Min Act: -0.1700

Data Index: 4836668 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.8032. Min Act: -0.1700

Data Index: 4577796 (Open Web Text)

Max Activating Token Index: 419

Text #8

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.7114. Min Act: -0.1700

Data Index: 6193257 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6951. Min Act: -0.1700

Data Index: 2895270 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6725. Min Act: -0.1700

Data Index: 2505487 (Open Web Text)

Max Activating Token Index: 893

Text #11

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6816. Min Act: -0.1700

Data Index: 5285410 (Open Web Text)

Max Activating Token Index: 760

Text #12

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6772. Min Act: -0.1700

Data Index: 5264136 (Open Web Text)

Max Activating Token Index: 853

Text #13

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6719. Min Act: -0.1700

Data Index: 4335643 (Open Web Text)

Max Activating Token Index: 325

Text #14

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6718. Min Act: -0.1700

Data Index: 304355 (Open Web Text)

Max Activating Token Index: 496

Text #15

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6585. Min Act: -0.1700

Data Index: 4951325 (Open Web Text)

Max Activating Token Index: 843

Text #16

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6568. Min Act: -0.1700

Data Index: 8590109 (Open Web Text)

Max Activating Token Index: 583

Text #17

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6363. Min Act: -0.1700

Data Index: 2676212 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6550. Min Act: -0.1700

Data Index: 8185479 (Open Web Text)

Max Activating Token Index: 248

Text #19

Max Range: 4.0583. Min Range: -4.0583

Max Act: 3.6156. Min Act: -0.1700

Data Index: 7711522 (Open Web Text)

Max Activating Token Index: 625