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

Dataset: Open Web Text

Neuron 586 in Layer 5

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: 5.9233. Min Range: -5.9233

Max Act: 5.9233. Min Act: -0.1700

Data Index: 768991 (Open Web Text)

Max Activating Token Index: 758

Text #1

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.9221. Min Act: -0.1700

Data Index: 840950 (Open Web Text)

Max Activating Token Index: 992

Text #2

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.8584. Min Act: -0.1700

Data Index: 105582 (Open Web Text)

Max Activating Token Index: 648

Text #3

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.8540. Min Act: -0.1700

Data Index: 5326252 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.8225. Min Act: -0.1700

Data Index: 3354020 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.8800. Min Act: -0.1700

Data Index: 128778 (Open Web Text)

Max Activating Token Index: 950

Text #6

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7986. Min Act: -0.1700

Data Index: 1672165 (Open Web Text)

Max Activating Token Index: 653

Text #7

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7842. Min Act: -0.1700

Data Index: 5763549 (Open Web Text)

Max Activating Token Index: 939

Text #8

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.8317. Min Act: -0.1700

Data Index: 3452307 (Open Web Text)

Max Activating Token Index: 967

Text #9

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.8221. Min Act: -0.1700

Data Index: 723708 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7930. Min Act: -0.1700

Data Index: 8706811 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7606. Min Act: -0.1700

Data Index: 993082 (Open Web Text)

Max Activating Token Index: 279

Text #12

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7634. Min Act: -0.1700

Data Index: 6747962 (Open Web Text)

Max Activating Token Index: 825

Text #13

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7892. Min Act: -0.1700

Data Index: 2521326 (Open Web Text)

Max Activating Token Index: 735

Text #14

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.8353. Min Act: -0.1700

Data Index: 1910477 (Open Web Text)

Max Activating Token Index: 963

Text #15

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7948. Min Act: -0.1700

Data Index: 1329561 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.8249. Min Act: -0.1700

Data Index: 7939560 (Open Web Text)

Max Activating Token Index: 881

Text #17

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7419. Min Act: -0.1700

Data Index: 1136487 (Open Web Text)

Max Activating Token Index: 667

Text #18

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7398. Min Act: -0.1700

Data Index: 4891208 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 5.9233. Min Range: -5.9233

Max Act: 5.7548. Min Act: -0.1700

Data Index: 6254956 (Open Web Text)

Max Activating Token Index: 974