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

Dataset: Open Web Text

Neuron 2602 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: 2.0696. Min Range: -2.0696

Max Act: 2.0696. Min Act: -0.1700

Data Index: 231590 (Open Web Text)

Max Activating Token Index: 478

Text #1

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.9333. Min Act: -0.1700

Data Index: 1831477 (Open Web Text)

Max Activating Token Index: 698

Text #2

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.9298. Min Act: -0.1700

Data Index: 2434714 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.9146. Min Act: -0.1700

Data Index: 8604120 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.9211. Min Act: -0.1700

Data Index: 2208425 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.9091. Min Act: -0.1700

Data Index: 5803415 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.9055. Min Act: -0.1700

Data Index: 3090842 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8994. Min Act: -0.1700

Data Index: 4318512 (Open Web Text)

Max Activating Token Index: 934

Text #8

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8886. Min Act: -0.1700

Data Index: 3523522 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8823. Min Act: -0.1700

Data Index: 128015 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8839. Min Act: -0.1700

Data Index: 8290863 (Open Web Text)

Max Activating Token Index: 849

Text #11

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8699. Min Act: -0.1700

Data Index: 6651070 (Open Web Text)

Max Activating Token Index: 900

Text #12

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8761. Min Act: -0.1700

Data Index: 4400180 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8517. Min Act: -0.1700

Data Index: 2074775 (Open Web Text)

Max Activating Token Index: 203

Text #14

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8423. Min Act: -0.1700

Data Index: 7243736 (Open Web Text)

Max Activating Token Index: 219

Text #15

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8500. Min Act: -0.1700

Data Index: 618491 (Open Web Text)

Max Activating Token Index: 127

Text #16

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8498. Min Act: -0.1700

Data Index: 8725497 (Open Web Text)

Max Activating Token Index: 576

Text #17

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8484. Min Act: -0.1700

Data Index: 4780695 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8374. Min Act: -0.1700

Data Index: 2149516 (Open Web Text)

Max Activating Token Index: 493

Text #19

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8496. Min Act: -0.1700

Data Index: 681822 (Open Web Text)

Max Activating Token Index: 16