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

Dataset: Open Web Text

Neuron 475 in Layer 6

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: 4.3185. Min Range: -4.3185

Max Act: 4.3185. Min Act: -0.1700

Data Index: 6924714 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 4.3185. Min Range: -4.3185

Max Act: 4.2112. Min Act: -0.1700

Data Index: 1808211 (Open Web Text)

Max Activating Token Index: 139

Text #2

Max Range: 4.3185. Min Range: -4.3185

Max Act: 4.1926. Min Act: -0.1700

Data Index: 3215955 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 4.3185. Min Range: -4.3185

Max Act: 4.1234. Min Act: -0.1700

Data Index: 2306265 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 4.3185. Min Range: -4.3185

Max Act: 4.0776. Min Act: -0.1700

Data Index: 227893 (Open Web Text)

Max Activating Token Index: 996

Text #5

Max Range: 4.3185. Min Range: -4.3185

Max Act: 4.0467. Min Act: -0.1700

Data Index: 548513 (Open Web Text)

Max Activating Token Index: 698

Text #6

Max Range: 4.3185. Min Range: -4.3185

Max Act: 4.0464. Min Act: -0.1700

Data Index: 180162 (Open Web Text)

Max Activating Token Index: 131

Text #7

Max Range: 4.3185. Min Range: -4.3185

Max Act: 4.0018. Min Act: -0.1700

Data Index: 1416218 (Open Web Text)

Max Activating Token Index: 648

Text #8

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.9339. Min Act: -0.1700

Data Index: 2335135 (Open Web Text)

Max Activating Token Index: 979

Text #9

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.9666. Min Act: -0.1700

Data Index: 1542098 (Open Web Text)

Max Activating Token Index: 654

Text #10

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.8980. Min Act: -0.1700

Data Index: 1624640 (Open Web Text)

Max Activating Token Index: 996

Text #11

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.9132. Min Act: -0.1700

Data Index: 3826638 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.9138. Min Act: -0.1700

Data Index: 7859714 (Open Web Text)

Max Activating Token Index: 1008

Text #13

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.9281. Min Act: -0.1700

Data Index: 8828890 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.8968. Min Act: -0.1700

Data Index: 5590908 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.8719. Min Act: -0.1700

Data Index: 1902549 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.8569. Min Act: -0.1700

Data Index: 6782028 (Open Web Text)

Max Activating Token Index: 899

Text #17

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.8775. Min Act: -0.1700

Data Index: 5906214 (Open Web Text)

Max Activating Token Index: 652

Text #18

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.9022. Min Act: -0.1700

Data Index: 7995598 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 4.3185. Min Range: -4.3185

Max Act: 3.8881. Min Act: -0.1700

Data Index: 4927779 (Open Web Text)

Max Activating Token Index: 423