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

Dataset: Open Web Text

Neuron 2079 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: 1.8697. Min Range: -1.8697

Max Act: 1.8697. Min Act: -0.1700

Data Index: 8533727 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.8650. Min Act: -0.1700

Data Index: 4598722 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7869. Min Act: -0.1700

Data Index: 2506981 (Open Web Text)

Max Activating Token Index: 377

Text #3

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7858. Min Act: -0.1700

Data Index: 6352342 (Open Web Text)

Max Activating Token Index: 374

Text #4

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7911. Min Act: -0.1700

Data Index: 1299295 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7920. Min Act: -0.1700

Data Index: 7494424 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7824. Min Act: -0.1700

Data Index: 8142498 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7826. Min Act: -0.1700

Data Index: 491607 (Open Web Text)

Max Activating Token Index: 90

Text #8

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7892. Min Act: -0.1700

Data Index: 1797029 (Open Web Text)

Max Activating Token Index: 698

Text #9

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7828. Min Act: -0.1700

Data Index: 6861426 (Open Web Text)

Max Activating Token Index: 674

Text #10

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7659. Min Act: -0.1700

Data Index: 7139591 (Open Web Text)

Max Activating Token Index: 489

Text #11

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7689. Min Act: -0.1700

Data Index: 250791 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7725. Min Act: -0.1700

Data Index: 2135633 (Open Web Text)

Max Activating Token Index: 48

Text #13

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7719. Min Act: -0.1700

Data Index: 1680519 (Open Web Text)

Max Activating Token Index: 62

Text #14

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7813. Min Act: -0.1700

Data Index: 5743032 (Open Web Text)

Max Activating Token Index: 308

Text #15

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7657. Min Act: -0.1700

Data Index: 7385412 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7669. Min Act: -0.1700

Data Index: 2587417 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7611. Min Act: -0.1700

Data Index: 1918491 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7556. Min Act: -0.1700

Data Index: 1343650 (Open Web Text)

Max Activating Token Index: 51

Text #19

Max Range: 1.8697. Min Range: -1.8697

Max Act: 1.7674. Min Act: -0.1700

Data Index: 8219526 (Open Web Text)

Max Activating Token Index: 39