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

Dataset: Open Web Text

Neuron 2202 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: 3.0845. Min Range: -3.0845

Max Act: 3.0845. Min Act: -0.1700

Data Index: 2465214 (Open Web Text)

Max Activating Token Index: 28

Text #1

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0579. Min Act: -0.1700

Data Index: 1671719 (Open Web Text)

Max Activating Token Index: 595

Text #2

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0425. Min Act: -0.1700

Data Index: 684770 (Open Web Text)

Max Activating Token Index: 46

Text #3

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0202. Min Act: -0.1700

Data Index: 1536735 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0445. Min Act: -0.1700

Data Index: 7729638 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0153. Min Act: -0.1700

Data Index: 6682932 (Open Web Text)

Max Activating Token Index: 361

Text #6

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0273. Min Act: -0.1700

Data Index: 5583570 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0144. Min Act: -0.1700

Data Index: 3835006 (Open Web Text)

Max Activating Token Index: 626

Text #8

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0057. Min Act: -0.1700

Data Index: 2845230 (Open Web Text)

Max Activating Token Index: 515

Text #9

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0113. Min Act: -0.1700

Data Index: 1331803 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0134. Min Act: -0.1700

Data Index: 5855248 (Open Web Text)

Max Activating Token Index: 776

Text #11

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0049. Min Act: -0.1700

Data Index: 7437697 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 3.0845. Min Range: -3.0845

Max Act: 2.9825. Min Act: -0.1700

Data Index: 4294128 (Open Web Text)

Max Activating Token Index: 588

Text #13

Max Range: 3.0845. Min Range: -3.0845

Max Act: 2.9785. Min Act: -0.1700

Data Index: 8830925 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 3.0845. Min Range: -3.0845

Max Act: 3.0033. Min Act: -0.1700

Data Index: 8808235 (Open Web Text)

Max Activating Token Index: 338

Text #15

Max Range: 3.0845. Min Range: -3.0845

Max Act: 2.9908. Min Act: -0.1700

Data Index: 6570009 (Open Web Text)

Max Activating Token Index: 241

Text #16

Max Range: 3.0845. Min Range: -3.0845

Max Act: 2.9859. Min Act: -0.1700

Data Index: 7827415 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 3.0845. Min Range: -3.0845

Max Act: 2.9666. Min Act: -0.1700

Data Index: 8048889 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 3.0845. Min Range: -3.0845

Max Act: 2.9794. Min Act: -0.1700

Data Index: 8172845 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 3.0845. Min Range: -3.0845

Max Act: 2.9782. Min Act: -0.1700

Data Index: 8804595 (Open Web Text)

Max Activating Token Index: 516