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

Dataset: Open Web Text

Neuron 1109 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: 6.1533. Min Range: -6.1533

Max Act: 6.1533. Min Act: -0.1700

Data Index: 548750 (Open Web Text)

Max Activating Token Index: 751

Text #1

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.1426. Min Act: -0.1700

Data Index: 8267707 (Open Web Text)

Max Activating Token Index: 940

Text #2

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.1344. Min Act: -0.1700

Data Index: 4904255 (Open Web Text)

Max Activating Token Index: 829

Text #3

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0993. Min Act: -0.1700

Data Index: 2029607 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0657. Min Act: -0.1700

Data Index: 302732 (Open Web Text)

Max Activating Token Index: 513

Text #5

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0552. Min Act: -0.1700

Data Index: 4927071 (Open Web Text)

Max Activating Token Index: 912

Text #6

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0791. Min Act: -0.1700

Data Index: 2743853 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0873. Min Act: -0.1700

Data Index: 4421065 (Open Web Text)

Max Activating Token Index: 698

Text #8

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0404. Min Act: -0.1700

Data Index: 1628837 (Open Web Text)

Max Activating Token Index: 331

Text #9

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0613. Min Act: -0.1700

Data Index: 3926737 (Open Web Text)

Max Activating Token Index: 933

Text #10

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0587. Min Act: -0.1700

Data Index: 3767548 (Open Web Text)

Max Activating Token Index: 601

Text #11

Max Range: 6.1533. Min Range: -6.1533

Max Act: 5.9866. Min Act: -0.1700

Data Index: 1547549 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0155. Min Act: -0.1700

Data Index: 4659230 (Open Web Text)

Max Activating Token Index: 650

Text #13

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0029. Min Act: -0.1700

Data Index: 5031553 (Open Web Text)

Max Activating Token Index: 719

Text #14

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0092. Min Act: -0.1700

Data Index: 635281 (Open Web Text)

Max Activating Token Index: 666

Text #15

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0128. Min Act: -0.1700

Data Index: 2945536 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0069. Min Act: -0.1700

Data Index: 2088348 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 6.1533. Min Range: -6.1533

Max Act: 6.0343. Min Act: -0.1700

Data Index: 2367456 (Open Web Text)

Max Activating Token Index: 832

Text #18

Max Range: 6.1533. Min Range: -6.1533

Max Act: 5.9893. Min Act: -0.1700

Data Index: 5537914 (Open Web Text)

Max Activating Token Index: 702

Text #19

Max Range: 6.1533. Min Range: -6.1533

Max Act: 5.9697. Min Act: -0.1700

Data Index: 3423406 (Open Web Text)

Max Activating Token Index: 460