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

Dataset: Open Web Text

Neuron 1290 in Layer 1

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: 1.7666. Min Range: -1.7666

Max Act: 1.7666. Min Act: -0.1700

Data Index: 1802294 (Open Web Text)

Max Activating Token Index: 30

Text #1

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7573. Min Act: -0.1700

Data Index: 3065300 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7517. Min Act: -0.1700

Data Index: 8145899 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7437. Min Act: -0.1700

Data Index: 3809570 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7499. Min Act: -0.1686

Data Index: 5613423 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7422. Min Act: -0.1700

Data Index: 6150122 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7418. Min Act: -0.1698

Data Index: 4672485 (Open Web Text)

Max Activating Token Index: 180

Text #7

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7439. Min Act: -0.1659

Data Index: 5456421 (Open Web Text)

Max Activating Token Index: 396

Text #8

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7398. Min Act: -0.1700

Data Index: 3796303 (Open Web Text)

Max Activating Token Index: 70

Text #9

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7283. Min Act: -0.1700

Data Index: 3921180 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7179. Min Act: -0.1700

Data Index: 6698155 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7211. Min Act: -0.1700

Data Index: 3869785 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7265. Min Act: -0.1700

Data Index: 2381519 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7216. Min Act: -0.1700

Data Index: 7293340 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7233. Min Act: -0.1700

Data Index: 8716256 (Open Web Text)

Max Activating Token Index: 788

Text #15

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7159. Min Act: -0.1700

Data Index: 5590499 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7150. Min Act: -0.1700

Data Index: 51747 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7120. Min Act: -0.1700

Data Index: 1690552 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7124. Min Act: -0.1700

Data Index: 4109115 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.7071. Min Act: -0.1700

Data Index: 888178 (Open Web Text)

Max Activating Token Index: 562