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

Dataset: Open Web Text

Neuron 1482 in Layer 1

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: 2.1038. Min Range: -2.1038

Max Act: 2.0956. Min Act: -0.1700

Data Index: 2172871 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.1038. Min Act: -0.1700

Data Index: 5574577 (Open Web Text)

Max Activating Token Index: 701

Text #2

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.1021. Min Act: -0.1700

Data Index: 610400 (Open Web Text)

Max Activating Token Index: 111

Text #3

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0933. Min Act: -0.1700

Data Index: 6381226 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0750. Min Act: -0.1700

Data Index: 7502387 (Open Web Text)

Max Activating Token Index: 51

Text #5

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0853. Min Act: -0.1700

Data Index: 5160506 (Open Web Text)

Max Activating Token Index: 674

Text #6

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0842. Min Act: -0.1700

Data Index: 5638410 (Open Web Text)

Max Activating Token Index: 793

Text #7

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0788. Min Act: -0.1700

Data Index: 4327997 (Open Web Text)

Max Activating Token Index: 107

Text #8

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0708. Min Act: -0.1700

Data Index: 7070989 (Open Web Text)

Max Activating Token Index: 47

Text #9

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0632. Min Act: -0.1699

Data Index: 4424571 (Open Web Text)

Max Activating Token Index: 767

Text #10

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0634. Min Act: -0.1700

Data Index: 8150388 (Open Web Text)

Max Activating Token Index: 106

Text #11

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0639. Min Act: -0.1700

Data Index: 1199066 (Open Web Text)

Max Activating Token Index: 437

Text #12

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0739. Min Act: -0.1700

Data Index: 7952128 (Open Web Text)

Max Activating Token Index: 454

Text #13

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0716. Min Act: -0.1700

Data Index: 5725671 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0584. Min Act: -0.1700

Data Index: 4490772 (Open Web Text)

Max Activating Token Index: 704

Text #15

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0600. Min Act: -0.1700

Data Index: 1075708 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0631. Min Act: -0.1700

Data Index: 4808847 (Open Web Text)

Max Activating Token Index: 445

Text #17

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0499. Min Act: -0.1700

Data Index: 7068228 (Open Web Text)

Max Activating Token Index: 453

Text #18

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0455. Min Act: -0.1700

Data Index: 1665010 (Open Web Text)

Max Activating Token Index: 633

Text #19

Max Range: 2.1038. Min Range: -2.1038

Max Act: 2.0451. Min Act: -0.1700

Data Index: 3732301 (Open Web Text)

Max Activating Token Index: 47