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

Dataset: Open Web Text

Neuron 1480 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: 3.0896. Min Range: -3.0896

Max Act: 3.0896. Min Act: -0.1700

Data Index: 705120 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 3.0896. Min Range: -3.0896

Max Act: 3.0439. Min Act: -0.1700

Data Index: 7352842 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 3.0896. Min Range: -3.0896

Max Act: 3.0306. Min Act: -0.1700

Data Index: 1536219 (Open Web Text)

Max Activating Token Index: 340

Text #3

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9977. Min Act: -0.1700

Data Index: 1805273 (Open Web Text)

Max Activating Token Index: 511

Text #4

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9771. Min Act: -0.1700

Data Index: 8135122 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9676. Min Act: -0.1700

Data Index: 4323546 (Open Web Text)

Max Activating Token Index: 63

Text #6

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9619. Min Act: -0.1700

Data Index: 6356112 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9437. Min Act: -0.1700

Data Index: 8749247 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9438. Min Act: -0.1700

Data Index: 8756253 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9143. Min Act: -0.1700

Data Index: 8749245 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9071. Min Act: -0.1700

Data Index: 2613341 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9311. Min Act: -0.1700

Data Index: 5943595 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9305. Min Act: -0.1700

Data Index: 1749466 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9052. Min Act: -0.1700

Data Index: 4210902 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.8725. Min Act: -0.1700

Data Index: 2421823 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.8765. Min Act: -0.1700

Data Index: 4862676 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.8722. Min Act: -0.1700

Data Index: 3013803 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.8694. Min Act: -0.1700

Data Index: 1730388 (Open Web Text)

Max Activating Token Index: 119

Text #18

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.8829. Min Act: -0.1700

Data Index: 5943592 (Open Web Text)

Max Activating Token Index: 120

Text #19

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.8356. Min Act: -0.1700

Data Index: 778248 (Open Web Text)

Max Activating Token Index: 519