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

Dataset: Open Web Text

Neuron 1274 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: 3.5546. Min Range: -3.5546

Max Act: 3.5546. Min Act: -0.1700

Data Index: 6431491 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.5288. Min Act: -0.1700

Data Index: 5746238 (Open Web Text)

Max Activating Token Index: 754

Text #2

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4797. Min Act: -0.1700

Data Index: 8266144 (Open Web Text)

Max Activating Token Index: 905

Text #3

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4424. Min Act: -0.1700

Data Index: 7878683 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4524. Min Act: -0.1700

Data Index: 182550 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4533. Min Act: -0.1700

Data Index: 1683847 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4087. Min Act: -0.1700

Data Index: 7773162 (Open Web Text)

Max Activating Token Index: 713

Text #7

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4163. Min Act: -0.1700

Data Index: 7722558 (Open Web Text)

Max Activating Token Index: 727

Text #8

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4027. Min Act: -0.1700

Data Index: 7225106 (Open Web Text)

Max Activating Token Index: 653

Text #9

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4473. Min Act: -0.1700

Data Index: 8516677 (Open Web Text)

Max Activating Token Index: 530

Text #10

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4116. Min Act: -0.1700

Data Index: 2201153 (Open Web Text)

Max Activating Token Index: 805

Text #11

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.4003. Min Act: -0.1700

Data Index: 1542129 (Open Web Text)

Max Activating Token Index: 452

Text #12

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.3796. Min Act: -0.1700

Data Index: 8154191 (Open Web Text)

Max Activating Token Index: 686

Text #13

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.3672. Min Act: -0.1700

Data Index: 8626025 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.3921. Min Act: -0.1700

Data Index: 4010732 (Open Web Text)

Max Activating Token Index: 912

Text #15

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.3911. Min Act: -0.1700

Data Index: 2013724 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.3738. Min Act: -0.1700

Data Index: 8090882 (Open Web Text)

Max Activating Token Index: 778

Text #17

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.3684. Min Act: -0.1700

Data Index: 860792 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.3684. Min Act: -0.1700

Data Index: 3632291 (Open Web Text)

Max Activating Token Index: 409

Text #19

Max Range: 3.5546. Min Range: -3.5546

Max Act: 3.3683. Min Act: -0.1700

Data Index: 5801409 (Open Web Text)

Max Activating Token Index: 736