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

Dataset: Open Web Text

Neuron 714 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: 1.6812. Min Range: -1.6812

Max Act: 1.6812. Min Act: -0.1700

Data Index: 1537207 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.6224. Min Act: -0.1596

Data Index: 205556 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.6252. Min Act: -0.1700

Data Index: 4076560 (Open Web Text)

Max Activating Token Index: 960

Text #3

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.6180. Min Act: -0.1694

Data Index: 7161498 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.6101. Min Act: -0.1700

Data Index: 408602 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5853. Min Act: -0.1639

Data Index: 4836947 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5796. Min Act: -0.1700

Data Index: 2558147 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1697

Data Index: 1011378 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1699

Data Index: 414548 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1680

Data Index: 330225 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1440

Data Index: 845261 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1581

Data Index: 763833 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1693

Data Index: 285945 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1700

Data Index: 597054 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1677

Data Index: 760869 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1668

Data Index: 773004 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1600

Data Index: 713986 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1626

Data Index: 1086791 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1670

Data Index: 45098 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 1.6812. Min Range: -1.6812

Max Act: 1.5733. Min Act: -0.1693

Data Index: 1194218 (Open Web Text)

Max Activating Token Index: 1