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

Dataset: Open Web Text

Neuron 2938 in Layer 0

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: 4.9313. Min Range: -4.9313

Max Act: 4.9313. Min Act: -0.1700

Data Index: 4249495 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.8458. Min Act: -0.1700

Data Index: 1834277 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.8750. Min Act: -0.1700

Data Index: 5880179 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.8172. Min Act: -0.1700

Data Index: 4304673 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7539. Min Act: -0.1700

Data Index: 6430443 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7676. Min Act: -0.1700

Data Index: 2821869 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7588. Min Act: -0.1700

Data Index: 5461082 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7521. Min Act: -0.1700

Data Index: 6622505 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7147. Min Act: -0.1700

Data Index: 4385822 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7186. Min Act: -0.1700

Data Index: 4365144 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7220. Min Act: -0.1700

Data Index: 8332983 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7404. Min Act: -0.1700

Data Index: 2349021 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7155. Min Act: -0.1700

Data Index: 1408183 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7309. Min Act: -0.1700

Data Index: 6658966 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7086. Min Act: -0.1700

Data Index: 6201489 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7031. Min Act: -0.1700

Data Index: 38951 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.6848. Min Act: -0.1700

Data Index: 2442970 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7058. Min Act: -0.1700

Data Index: 1222472 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7068. Min Act: -0.1700

Data Index: 6496239 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.6914. Min Act: -0.1700

Data Index: 894257 (Open Web Text)

Max Activating Token Index: 11