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

Dataset: Open Web Text

Neuron 2863 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: 3.0852. Min Range: -3.0852

Max Act: 3.0756. Min Act: -0.1700

Data Index: 4921131 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0852. Min Act: -0.1700

Data Index: 7131874 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0561. Min Act: -0.1700

Data Index: 2982936 (Open Web Text)

Max Activating Token Index: 728

Text #3

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0463. Min Act: -0.1700

Data Index: 6723926 (Open Web Text)

Max Activating Token Index: 127

Text #4

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0475. Min Act: -0.1700

Data Index: 3062703 (Open Web Text)

Max Activating Token Index: 272

Text #5

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0415. Min Act: -0.1700

Data Index: 8508386 (Open Web Text)

Max Activating Token Index: 966

Text #6

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0150. Min Act: -0.1700

Data Index: 4821399 (Open Web Text)

Max Activating Token Index: 503

Text #7

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9976. Min Act: -0.1700

Data Index: 4288213 (Open Web Text)

Max Activating Token Index: 241

Text #8

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0034. Min Act: -0.1700

Data Index: 1134516 (Open Web Text)

Max Activating Token Index: 866

Text #9

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9987. Min Act: -0.1700

Data Index: 3495780 (Open Web Text)

Max Activating Token Index: 796

Text #10

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0031. Min Act: -0.1700

Data Index: 1758536 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0015. Min Act: -0.1700

Data Index: 748943 (Open Web Text)

Max Activating Token Index: 687

Text #12

Max Range: 3.0852. Min Range: -3.0852

Max Act: 3.0105. Min Act: -0.1700

Data Index: 3893906 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9868. Min Act: -0.1700

Data Index: 3821757 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9837. Min Act: -0.1700

Data Index: 5088217 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9834. Min Act: -0.1700

Data Index: 6641542 (Open Web Text)

Max Activating Token Index: 207

Text #16

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9639. Min Act: -0.1700

Data Index: 1471086 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9689. Min Act: -0.1700

Data Index: 1645679 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9394. Min Act: -0.1700

Data Index: 2045786 (Open Web Text)

Max Activating Token Index: 776

Text #19

Max Range: 3.0852. Min Range: -3.0852

Max Act: 2.9638. Min Act: -0.1700

Data Index: 1676068 (Open Web Text)

Max Activating Token Index: 233