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

Dataset: Open Web Text

Neuron 562 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: 3.7011. Min Range: -3.7011

Max Act: 3.7011. Min Act: -0.1700

Data Index: 7336765 (Open Web Text)

Max Activating Token Index: 298

Text #1

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6575. Min Act: -0.1700

Data Index: 4540490 (Open Web Text)

Max Activating Token Index: 529

Text #2

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6602. Min Act: -0.1700

Data Index: 8662666 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6412. Min Act: -0.1700

Data Index: 6180147 (Open Web Text)

Max Activating Token Index: 94

Text #4

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6340. Min Act: -0.1700

Data Index: 8117678 (Open Web Text)

Max Activating Token Index: 171

Text #5

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6288. Min Act: -0.1700

Data Index: 5822583 (Open Web Text)

Max Activating Token Index: 470

Text #6

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6536. Min Act: -0.1700

Data Index: 8440723 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6388. Min Act: -0.1700

Data Index: 4932647 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6032. Min Act: -0.1700

Data Index: 7556886 (Open Web Text)

Max Activating Token Index: 502

Text #9

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5894. Min Act: -0.1700

Data Index: 5861126 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6119. Min Act: -0.1700

Data Index: 4733146 (Open Web Text)

Max Activating Token Index: 402

Text #11

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.6121. Min Act: -0.1700

Data Index: 8228102 (Open Web Text)

Max Activating Token Index: 107

Text #12

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5989. Min Act: -0.1700

Data Index: 3404631 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5800. Min Act: -0.1700

Data Index: 1035067 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5928. Min Act: -0.1700

Data Index: 1019190 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5983. Min Act: -0.1700

Data Index: 400571 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5880. Min Act: -0.1700

Data Index: 5008924 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5809. Min Act: -0.1700

Data Index: 247113 (Open Web Text)

Max Activating Token Index: 226

Text #18

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5842. Min Act: -0.1700

Data Index: 3209635 (Open Web Text)

Max Activating Token Index: 599

Text #19

Max Range: 3.7011. Min Range: -3.7011

Max Act: 3.5847. Min Act: -0.1700

Data Index: 5882842 (Open Web Text)

Max Activating Token Index: 298