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

Dataset: Open Web Text

Neuron 877 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: 3.9512. Min Range: -3.9512

Max Act: 3.9512. Min Act: -0.1700

Data Index: 7851307 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.8513. Min Act: -0.1700

Data Index: 1560345 (Open Web Text)

Max Activating Token Index: 508

Text #2

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.8664. Min Act: -0.1700

Data Index: 813993 (Open Web Text)

Max Activating Token Index: 866

Text #3

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.8388. Min Act: -0.1700

Data Index: 7709043 (Open Web Text)

Max Activating Token Index: 445

Text #4

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7740. Min Act: -0.1700

Data Index: 2437707 (Open Web Text)

Max Activating Token Index: 752

Text #5

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7697. Min Act: -0.1700

Data Index: 1964606 (Open Web Text)

Max Activating Token Index: 768

Text #6

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7695. Min Act: -0.1700

Data Index: 5869570 (Open Web Text)

Max Activating Token Index: 430

Text #7

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7613. Min Act: -0.1700

Data Index: 276776 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7282. Min Act: -0.1700

Data Index: 6337965 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7284. Min Act: -0.1700

Data Index: 4508219 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7194. Min Act: -0.1700

Data Index: 7919696 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7230. Min Act: -0.1700

Data Index: 7805984 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7030. Min Act: -0.1700

Data Index: 4291826 (Open Web Text)

Max Activating Token Index: 363

Text #13

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.6762. Min Act: -0.1700

Data Index: 8251154 (Open Web Text)

Max Activating Token Index: 162

Text #14

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.6834. Min Act: -0.1700

Data Index: 83062 (Open Web Text)

Max Activating Token Index: 290

Text #15

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.6759. Min Act: -0.1700

Data Index: 5259688 (Open Web Text)

Max Activating Token Index: 595

Text #16

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.7072. Min Act: -0.1700

Data Index: 7554960 (Open Web Text)

Max Activating Token Index: 507

Text #17

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.6888. Min Act: -0.1700

Data Index: 948156 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.6804. Min Act: -0.1700

Data Index: 6262326 (Open Web Text)

Max Activating Token Index: 491

Text #19

Max Range: 3.9512. Min Range: -3.9512

Max Act: 3.6953. Min Act: -0.1700

Data Index: 6236738 (Open Web Text)

Max Activating Token Index: 733