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

Dataset: Open Web Text

Neuron 413 in Layer 3

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: 3.9905. Min Range: -3.9905

Max Act: 3.9905. Min Act: -0.1700

Data Index: 6791693 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8868. Min Act: -0.1700

Data Index: 6791699 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8426. Min Act: -0.1700

Data Index: 6791695 (Open Web Text)

Max Activating Token Index: 137

Text #3

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8280. Min Act: -0.1700

Data Index: 6791700 (Open Web Text)

Max Activating Token Index: 113

Text #4

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8404. Min Act: -0.1700

Data Index: 6791701 (Open Web Text)

Max Activating Token Index: 80

Text #5

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8126. Min Act: -0.1700

Data Index: 6791702 (Open Web Text)

Max Activating Token Index: 296

Text #6

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8251. Min Act: -0.1700

Data Index: 6791712 (Open Web Text)

Max Activating Token Index: 114

Text #7

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8018. Min Act: -0.1700

Data Index: 6791711 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7891. Min Act: -0.1700

Data Index: 6791713 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7704. Min Act: -0.1700

Data Index: 6722091 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7565. Min Act: -0.1700

Data Index: 6791709 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.6990. Min Act: -0.1700

Data Index: 6791696 (Open Web Text)

Max Activating Token Index: 287

Text #12

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7179. Min Act: -0.1700

Data Index: 3062798 (Open Web Text)

Max Activating Token Index: 860

Text #13

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7075. Min Act: -0.1700

Data Index: 8429319 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7094. Min Act: -0.1700

Data Index: 6791703 (Open Web Text)

Max Activating Token Index: 156

Text #15

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7164. Min Act: -0.1700

Data Index: 6791707 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7105. Min Act: -0.1700

Data Index: 1430155 (Open Web Text)

Max Activating Token Index: 208

Text #17

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.6933. Min Act: -0.1700

Data Index: 6791704 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.6822. Min Act: -0.1700

Data Index: 6770531 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.6745. Min Act: -0.1700

Data Index: 6791708 (Open Web Text)

Max Activating Token Index: 82