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

Dataset: Open Web Text

Neuron 594 in Layer 5

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: 3.1876. Min Range: -3.1876

Max Act: 3.1876. Min Act: -0.1700

Data Index: 3676880 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.9556. Min Act: -0.1700

Data Index: 3408450 (Open Web Text)

Max Activating Token Index: 78

Text #2

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.9417. Min Act: -0.1700

Data Index: 7889539 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.9208. Min Act: -0.1700

Data Index: 8319841 (Open Web Text)

Max Activating Token Index: 840

Text #4

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8519. Min Act: -0.1700

Data Index: 7003997 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8785. Min Act: -0.1700

Data Index: 7734626 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8150. Min Act: -0.1700

Data Index: 8167239 (Open Web Text)

Max Activating Token Index: 944

Text #7

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8041. Min Act: -0.1700

Data Index: 430237 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8598. Min Act: -0.1700

Data Index: 7862516 (Open Web Text)

Max Activating Token Index: 852

Text #9

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8128. Min Act: -0.1700

Data Index: 7718489 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8353. Min Act: -0.1700

Data Index: 866352 (Open Web Text)

Max Activating Token Index: 551

Text #11

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8122. Min Act: -0.1700

Data Index: 7840392 (Open Web Text)

Max Activating Token Index: 364

Text #12

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.8089. Min Act: -0.1700

Data Index: 2589663 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.7827. Min Act: -0.1700

Data Index: 4022162 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.7851. Min Act: -0.1700

Data Index: 3479336 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.7703. Min Act: -0.1700

Data Index: 6045080 (Open Web Text)

Max Activating Token Index: 248

Text #16

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.7661. Min Act: -0.1700

Data Index: 4898947 (Open Web Text)

Max Activating Token Index: 721

Text #17

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.7706. Min Act: -0.1700

Data Index: 3771832 (Open Web Text)

Max Activating Token Index: 695

Text #18

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.7663. Min Act: -0.1700

Data Index: 4837216 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 3.1876. Min Range: -3.1876

Max Act: 2.7705. Min Act: -0.1700

Data Index: 6684505 (Open Web Text)

Max Activating Token Index: 64