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

Dataset: Open Web Text

Neuron 829 in Layer 0

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: 2.0556. Min Range: -2.0556

Max Act: 2.0556. Min Act: -0.1690

Data Index: 1631591 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.0556. Min Range: -2.0556

Max Act: 2.0266. Min Act: -0.1700

Data Index: 7587506 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.0556. Min Range: -2.0556

Max Act: 2.0243. Min Act: -0.1700

Data Index: 1623309 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.0556. Min Range: -2.0556

Max Act: 2.0266. Min Act: -0.1695

Data Index: 799945 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.9298. Min Act: -0.1694

Data Index: 8734923 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.9105. Min Act: -0.1699

Data Index: 2641219 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.9107. Min Act: -0.1700

Data Index: 1530237 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8971. Min Act: -0.1695

Data Index: 4119792 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1700

Data Index: 804888 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1692

Data Index: 1510984 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1699

Data Index: 1445333 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1700

Data Index: 197184 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1700

Data Index: 1281902 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1699

Data Index: 589591 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1682

Data Index: 20718 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1700

Data Index: 1431082 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1700

Data Index: 933877 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1700

Data Index: 1465523 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1700

Data Index: 1367088 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.8909. Min Act: -0.1699

Data Index: 1643936 (Open Web Text)

Max Activating Token Index: 1