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

Dataset: Open Web Text

Neuron 110 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: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.1700

Data Index: 850425 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7762. Min Act: -0.1700

Data Index: 1804176 (Open Web Text)

Max Activating Token Index: 564

Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7135. Min Act: -0.1700

Data Index: 1647842 (Open Web Text)

Max Activating Token Index: 576

Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6899. Min Act: -0.1700

Data Index: 7359755 (Open Web Text)

Max Activating Token Index: 539

Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6829. Min Act: -0.1700

Data Index: 996132 (Open Web Text)

Max Activating Token Index: 571

Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6866. Min Act: -0.1700

Data Index: 1273512 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6842. Min Act: -0.1700

Data Index: 6639342 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6879. Min Act: -0.1700

Data Index: 3227503 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6762. Min Act: -0.1700

Data Index: 7156222 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6764. Min Act: -0.1700

Data Index: 4626628 (Open Web Text)

Max Activating Token Index: 569

Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6745. Min Act: -0.1700

Data Index: 8660017 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6804. Min Act: -0.1700

Data Index: 2287727 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6727. Min Act: -0.1700

Data Index: 8135735 (Open Web Text)

Max Activating Token Index: 567

Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6816. Min Act: -0.1700

Data Index: 2474365 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6737. Min Act: -0.1700

Data Index: 92407 (Open Web Text)

Max Activating Token Index: 562

Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6686. Min Act: -0.1700

Data Index: 6555068 (Open Web Text)

Max Activating Token Index: 562

Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6791. Min Act: -0.1700

Data Index: 3819082 (Open Web Text)

Max Activating Token Index: 555

Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6626. Min Act: -0.1700

Data Index: 5279431 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6744. Min Act: -0.1700

Data Index: 2306019 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6750. Min Act: -0.1700

Data Index: 3786595 (Open Web Text)

Max Activating Token Index: 558