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

Dataset: Open Web Text

Neuron 2770 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: 1.8756. Min Range: -1.8756

Max Act: 1.8756. Min Act: -0.1699

Data Index: 6849031 (Open Web Text)

Max Activating Token Index: 603

Text #1

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.8029. Min Act: -0.1700

Data Index: 7418809 (Open Web Text)

Max Activating Token Index: 933

Text #2

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7833. Min Act: -0.1699

Data Index: 2019206 (Open Web Text)

Max Activating Token Index: 461

Text #3

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7852. Min Act: -0.1680

Data Index: 6981340 (Open Web Text)

Max Activating Token Index: 642

Text #4

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7838. Min Act: -0.1700

Data Index: 5308966 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7899. Min Act: -0.1700

Data Index: 6810449 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7849. Min Act: -0.1700

Data Index: 6192351 (Open Web Text)

Max Activating Token Index: 407

Text #7

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7680. Min Act: -0.1689

Data Index: 4780794 (Open Web Text)

Max Activating Token Index: 993

Text #8

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7515. Min Act: -0.1688

Data Index: 7260060 (Open Web Text)

Max Activating Token Index: 205

Text #9

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7522. Min Act: -0.1700

Data Index: 5631732 (Open Web Text)

Max Activating Token Index: 808

Text #10

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7343. Min Act: -0.1700

Data Index: 8526901 (Open Web Text)

Max Activating Token Index: 857

Text #11

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7128. Min Act: -0.1700

Data Index: 1759600 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6997. Min Act: -0.1698

Data Index: 3240227 (Open Web Text)

Max Activating Token Index: 951

Text #13

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.7201. Min Act: -0.1700

Data Index: 6752130 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6914. Min Act: -0.1698

Data Index: 5151619 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6887. Min Act: -0.1700

Data Index: 8730888 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6838. Min Act: -0.1698

Data Index: 1614440 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6786. Min Act: -0.1700

Data Index: 5268709 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6792. Min Act: -0.1700

Data Index: 1544409 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6531. Min Act: -0.1673

Data Index: 5684644 (Open Web Text)

Max Activating Token Index: 730