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

Dataset: Open Web Text

Neuron 2154 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: 3.8733. Min Range: -3.8733

Max Act: 3.8733. Min Act: -0.1700

Data Index: 1167839 (Open Web Text)

Max Activating Token Index: 527

Text #1

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.8481. Min Act: -0.1700

Data Index: 5123614 (Open Web Text)

Max Activating Token Index: 609

Text #2

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.8677. Min Act: -0.1700

Data Index: 3289331 (Open Web Text)

Max Activating Token Index: 734

Text #3

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.8473. Min Act: -0.1700

Data Index: 6141953 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.8097. Min Act: -0.1700

Data Index: 5252992 (Open Web Text)

Max Activating Token Index: 699

Text #5

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.8501. Min Act: -0.1700

Data Index: 2502989 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.8088. Min Act: -0.1700

Data Index: 1842440 (Open Web Text)

Max Activating Token Index: 377

Text #7

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.8016. Min Act: -0.1700

Data Index: 4445547 (Open Web Text)

Max Activating Token Index: 223

Text #8

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7753. Min Act: -0.1700

Data Index: 5926637 (Open Web Text)

Max Activating Token Index: 629

Text #9

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7928. Min Act: -0.1700

Data Index: 2603618 (Open Web Text)

Max Activating Token Index: 844

Text #10

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7982. Min Act: -0.1700

Data Index: 1016112 (Open Web Text)

Max Activating Token Index: 882

Text #11

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.8126. Min Act: -0.1700

Data Index: 2064945 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7268. Min Act: -0.1700

Data Index: 7901259 (Open Web Text)

Max Activating Token Index: 740

Text #13

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7847. Min Act: -0.1700

Data Index: 944474 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7532. Min Act: -0.1700

Data Index: 5410340 (Open Web Text)

Max Activating Token Index: 354

Text #15

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7347. Min Act: -0.1700

Data Index: 7935460 (Open Web Text)

Max Activating Token Index: 795

Text #16

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7789. Min Act: -0.1700

Data Index: 2698773 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7944. Min Act: -0.1700

Data Index: 1695277 (Open Web Text)

Max Activating Token Index: 495

Text #18

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7529. Min Act: -0.1700

Data Index: 2260691 (Open Web Text)

Max Activating Token Index: 897

Text #19

Max Range: 3.8733. Min Range: -3.8733

Max Act: 3.7640. Min Act: -0.1700

Data Index: 5994648 (Open Web Text)

Max Activating Token Index: 115