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

Dataset: Open Web Text

Neuron 2355 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: 0.8709. Min Range: -0.8709

Max Act: 0.8709. Min Act: -0.1552

Data Index: 1454604 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8595. Min Act: -0.1674

Data Index: 706640 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8474. Min Act: -0.1577

Data Index: 8796001 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8427. Min Act: -0.1609

Data Index: 1597548 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8388. Min Act: -0.1611

Data Index: 4925124 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8375. Min Act: -0.1651

Data Index: 4496096 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8269. Min Act: -0.1685

Data Index: 7515846 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8143. Min Act: -0.1651

Data Index: 8517960 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8208. Min Act: -0.1655

Data Index: 5074311 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8109. Min Act: -0.1596

Data Index: 2899736 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8183. Min Act: -0.1607

Data Index: 5743164 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8037. Min Act: -0.1667

Data Index: 5583874 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8117. Min Act: -0.1677

Data Index: 1607030 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8068. Min Act: -0.1608

Data Index: 4952085 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8081. Min Act: -0.1590

Data Index: 8796000 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8050. Min Act: -0.1682

Data Index: 6712535 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8078. Min Act: -0.1661

Data Index: 3532518 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8024. Min Act: -0.1609

Data Index: 5819510 (Open Web Text)

Max Activating Token Index: 38

Text #18

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8026. Min Act: -0.1351

Data Index: 7714068 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8084. Min Act: -0.1677

Data Index: 5064638 (Open Web Text)

Max Activating Token Index: 42