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

Dataset: Open Web Text

Neuron 676 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: 5.3706. Min Range: -5.3706

Max Act: 5.3706. Min Act: -0.1700

Data Index: 3658893 (Open Web Text)

Max Activating Token Index: 177

Text #1

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2803. Min Act: -0.1700

Data Index: 6928716 (Open Web Text)

Max Activating Token Index: 972

Text #2

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2855. Min Act: -0.1700

Data Index: 2397609 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2827. Min Act: -0.1700

Data Index: 113314 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2691. Min Act: -0.1700

Data Index: 7993359 (Open Web Text)

Max Activating Token Index: 411

Text #5

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2813. Min Act: -0.1700

Data Index: 4735803 (Open Web Text)

Max Activating Token Index: 410

Text #6

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2283. Min Act: -0.1700

Data Index: 410808 (Open Web Text)

Max Activating Token Index: 218

Text #7

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2120. Min Act: -0.1700

Data Index: 1847848 (Open Web Text)

Max Activating Token Index: 908

Text #8

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2394. Min Act: -0.1700

Data Index: 6928713 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2714. Min Act: -0.1700

Data Index: 5640767 (Open Web Text)

Max Activating Token Index: 153

Text #10

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.1804. Min Act: -0.1700

Data Index: 4859882 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2220. Min Act: -0.1700

Data Index: 5233628 (Open Web Text)

Max Activating Token Index: 342

Text #12

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2494. Min Act: -0.1700

Data Index: 6164525 (Open Web Text)

Max Activating Token Index: 704

Text #13

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2112. Min Act: -0.1700

Data Index: 8548618 (Open Web Text)

Max Activating Token Index: 890

Text #14

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.2387. Min Act: -0.1700

Data Index: 37903 (Open Web Text)

Max Activating Token Index: 963

Text #15

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.1988. Min Act: -0.1700

Data Index: 7110723 (Open Web Text)

Max Activating Token Index: 364

Text #16

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.1763. Min Act: -0.1700

Data Index: 1274640 (Open Web Text)

Max Activating Token Index: 360

Text #17

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.1709. Min Act: -0.1700

Data Index: 1274643 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.1680. Min Act: -0.1700

Data Index: 1350194 (Open Web Text)

Max Activating Token Index: 306

Text #19

Max Range: 5.3706. Min Range: -5.3706

Max Act: 5.1672. Min Act: -0.1700

Data Index: 59620 (Open Web Text)

Max Activating Token Index: 304