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

Dataset: Open Web Text

Neuron 1065 in Layer 3

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: 4.0508. Min Range: -4.0508

Max Act: 4.0508. Min Act: -0.1700

Data Index: 2664752 (Open Web Text)

Max Activating Token Index: 984

Text #1

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8570. Min Act: -0.1700

Data Index: 853106 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8496. Min Act: -0.1700

Data Index: 3717356 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7509. Min Act: -0.1700

Data Index: 2814926 (Open Web Text)

Max Activating Token Index: 557

Text #4

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8002. Min Act: -0.1700

Data Index: 5851736 (Open Web Text)

Max Activating Token Index: 423

Text #5

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8109. Min Act: -0.1700

Data Index: 2959978 (Open Web Text)

Max Activating Token Index: 943

Text #6

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8346. Min Act: -0.1700

Data Index: 7606172 (Open Web Text)

Max Activating Token Index: 289

Text #7

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7849. Min Act: -0.1700

Data Index: 2615731 (Open Web Text)

Max Activating Token Index: 408

Text #8

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7629. Min Act: -0.1700

Data Index: 5142165 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7590. Min Act: -0.1700

Data Index: 4282611 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7312. Min Act: -0.1700

Data Index: 7659451 (Open Web Text)

Max Activating Token Index: 617

Text #11

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7458. Min Act: -0.1700

Data Index: 184130 (Open Web Text)

Max Activating Token Index: 44

Text #12

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.6787. Min Act: -0.1700

Data Index: 8472798 (Open Web Text)

Max Activating Token Index: 942

Text #13

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7097. Min Act: -0.1700

Data Index: 8234418 (Open Web Text)

Max Activating Token Index: 920

Text #14

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7086. Min Act: -0.1700

Data Index: 6337176 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7211. Min Act: -0.1700

Data Index: 6500730 (Open Web Text)

Max Activating Token Index: 627

Text #16

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.6953. Min Act: -0.1700

Data Index: 7544834 (Open Web Text)

Max Activating Token Index: 185

Text #17

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7296. Min Act: -0.1700

Data Index: 7565682 (Open Web Text)

Max Activating Token Index: 591

Text #18

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7532. Min Act: -0.1700

Data Index: 2533425 (Open Web Text)

Max Activating Token Index: 971

Text #19

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7103. Min Act: -0.1700

Data Index: 5140815 (Open Web Text)

Max Activating Token Index: 555