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

Dataset: Open Web Text

Neuron 1877 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: 1.8741. Min Range: -1.8741

Max Act: 1.8741. Min Act: -0.1700

Data Index: 3271320 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8731. Min Act: -0.1700

Data Index: 5655547 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8597. Min Act: -0.1700

Data Index: 8005019 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8561. Min Act: -0.1700

Data Index: 7398640 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8506. Min Act: -0.1700

Data Index: 6726502 (Open Web Text)

Max Activating Token Index: 71

Text #5

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8284. Min Act: -0.1699

Data Index: 3582678 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8248. Min Act: -0.1700

Data Index: 6549845 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8142. Min Act: -0.1700

Data Index: 6984536 (Open Web Text)

Max Activating Token Index: 144

Text #8

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8240. Min Act: -0.1696

Data Index: 338324 (Open Web Text)

Max Activating Token Index: 647

Text #9

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8074. Min Act: -0.1700

Data Index: 2668181 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8068. Min Act: -0.1700

Data Index: 2108265 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8028. Min Act: -0.1700

Data Index: 6944673 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8037. Min Act: -0.1700

Data Index: 5430494 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8085. Min Act: -0.1700

Data Index: 6461193 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.8038. Min Act: -0.1700

Data Index: 8232735 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.7938. Min Act: -0.1700

Data Index: 6068661 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.7986. Min Act: -0.1700

Data Index: 777847 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.7940. Min Act: -0.1700

Data Index: 4159742 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.7870. Min Act: -0.1700

Data Index: 4500210 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 1.8741. Min Range: -1.8741

Max Act: 1.7848. Min Act: -0.1700

Data Index: 5109645 (Open Web Text)

Max Activating Token Index: 645