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

Dataset: Open Web Text

Neuron 1202 in Layer 2

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: 3.3890. Min Range: -3.3890

Max Act: 3.3890. Min Act: -0.1700

Data Index: 4192758 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2291. Min Act: -0.1700

Data Index: 5996642 (Open Web Text)

Max Activating Token Index: 158

Text #2

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.0066. Min Act: -0.1700

Data Index: 4638544 (Open Web Text)

Max Activating Token Index: 225

Text #3

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.9696. Min Act: -0.1700

Data Index: 5883421 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.9211. Min Act: -0.1700

Data Index: 1081539 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.9229. Min Act: -0.1700

Data Index: 3894149 (Open Web Text)

Max Activating Token Index: 612

Text #6

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8998. Min Act: -0.1700

Data Index: 410258 (Open Web Text)

Max Activating Token Index: 809

Text #7

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.9054. Min Act: -0.1700

Data Index: 6102809 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.9104. Min Act: -0.1700

Data Index: 5653 (Open Web Text)

Max Activating Token Index: 603

Text #9

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.9058. Min Act: -0.1700

Data Index: 8415315 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.9303. Min Act: -0.1700

Data Index: 683307 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.9028. Min Act: -0.1700

Data Index: 326530 (Open Web Text)

Max Activating Token Index: 696

Text #12

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8917. Min Act: -0.1700

Data Index: 2161564 (Open Web Text)

Max Activating Token Index: 854

Text #13

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8795. Min Act: -0.1700

Data Index: 4676498 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8928. Min Act: -0.1700

Data Index: 4914713 (Open Web Text)

Max Activating Token Index: 689

Text #15

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8736. Min Act: -0.1700

Data Index: 567415 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8776. Min Act: -0.1700

Data Index: 8392176 (Open Web Text)

Max Activating Token Index: 47

Text #17

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8504. Min Act: -0.1700

Data Index: 5091673 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8757. Min Act: -0.1700

Data Index: 1741889 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 3.3890. Min Range: -3.3890

Max Act: 2.8633. Min Act: -0.1700

Data Index: 5735987 (Open Web Text)

Max Activating Token Index: 333