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

Dataset: Open Web Text

Neuron 1775 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: 1.8688. Min Range: -1.8688

Max Act: 1.8688. Min Act: -0.1700

Data Index: 7398961 (Open Web Text)

Max Activating Token Index: 931

Text #1

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8392. Min Act: -0.1700

Data Index: 3821389 (Open Web Text)

Max Activating Token Index: 665

Text #2

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.8030. Min Act: -0.1700

Data Index: 8405152 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7979. Min Act: -0.1700

Data Index: 6220604 (Open Web Text)

Max Activating Token Index: 422

Text #4

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7803. Min Act: -0.1700

Data Index: 7204815 (Open Web Text)

Max Activating Token Index: 957

Text #5

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7904. Min Act: -0.1700

Data Index: 2509840 (Open Web Text)

Max Activating Token Index: 495

Text #6

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7910. Min Act: -0.1700

Data Index: 2749631 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7734. Min Act: -0.1700

Data Index: 1420021 (Open Web Text)

Max Activating Token Index: 405

Text #8

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7728. Min Act: -0.1700

Data Index: 2539688 (Open Web Text)

Max Activating Token Index: 70

Text #9

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7833. Min Act: -0.1700

Data Index: 843205 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7699. Min Act: -0.1700

Data Index: 5426918 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7638. Min Act: -0.1700

Data Index: 577252 (Open Web Text)

Max Activating Token Index: 1014

Text #12

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7750. Min Act: -0.1700

Data Index: 1415912 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7685. Min Act: -0.1700

Data Index: 1514871 (Open Web Text)

Max Activating Token Index: 258

Text #14

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7840. Min Act: -0.1700

Data Index: 7642488 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7598. Min Act: -0.1700

Data Index: 2636192 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7568. Min Act: -0.1700

Data Index: 4217097 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7640. Min Act: -0.1700

Data Index: 1351409 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7649. Min Act: -0.1700

Data Index: 3112708 (Open Web Text)

Max Activating Token Index: 736

Text #19

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7554. Min Act: -0.1700

Data Index: 3123977 (Open Web Text)

Max Activating Token Index: 457