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

Dataset: Open Web Text

Neuron 2927 in Layer 4

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: 3.0636. Min Range: -3.0636

Max Act: 3.0636. Min Act: -0.1700

Data Index: 8538342 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 3.0636. Min Range: -3.0636

Max Act: 3.0187. Min Act: -0.1700

Data Index: 5449869 (Open Web Text)

Max Activating Token Index: 153

Text #2

Max Range: 3.0636. Min Range: -3.0636

Max Act: 3.0518. Min Act: -0.1700

Data Index: 5104950 (Open Web Text)

Max Activating Token Index: 574

Text #3

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9828. Min Act: -0.1700

Data Index: 2279626 (Open Web Text)

Max Activating Token Index: 328

Text #4

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8966. Min Act: -0.1700

Data Index: 2539135 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9476. Min Act: -0.1700

Data Index: 501535 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9237. Min Act: -0.1700

Data Index: 3959877 (Open Web Text)

Max Activating Token Index: 472

Text #7

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9071. Min Act: -0.1700

Data Index: 7517957 (Open Web Text)

Max Activating Token Index: 729

Text #8

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8731. Min Act: -0.1700

Data Index: 1811559 (Open Web Text)

Max Activating Token Index: 611

Text #9

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9098. Min Act: -0.1700

Data Index: 7478723 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8652. Min Act: -0.1700

Data Index: 7145972 (Open Web Text)

Max Activating Token Index: 757

Text #11

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8728. Min Act: -0.1700

Data Index: 2349621 (Open Web Text)

Max Activating Token Index: 638

Text #12

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8971. Min Act: -0.1700

Data Index: 3798619 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8887. Min Act: -0.1700

Data Index: 1400697 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8454. Min Act: -0.1700

Data Index: 5829522 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8507. Min Act: -0.1700

Data Index: 4904123 (Open Web Text)

Max Activating Token Index: 538

Text #16

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8783. Min Act: -0.1700

Data Index: 1944932 (Open Web Text)

Max Activating Token Index: 360

Text #17

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8859. Min Act: -0.1700

Data Index: 8079223 (Open Web Text)

Max Activating Token Index: 340

Text #18

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8707. Min Act: -0.1700

Data Index: 5655393 (Open Web Text)

Max Activating Token Index: 285

Text #19

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.8638. Min Act: -0.1700

Data Index: 4416363 (Open Web Text)

Max Activating Token Index: 284