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

Dataset: Open Web Text

Neuron 332 in Layer 2

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: 3.9087. Min Range: -3.9087

Max Act: 3.8942. Min Act: -0.1700

Data Index: 6476382 (Open Web Text)

Max Activating Token Index: 979

Text #1

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.9087. Min Act: -0.1700

Data Index: 650437 (Open Web Text)

Max Activating Token Index: 80

Text #2

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.8365. Min Act: -0.1700

Data Index: 302493 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7971. Min Act: -0.1700

Data Index: 5226490 (Open Web Text)

Max Activating Token Index: 323

Text #4

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7738. Min Act: -0.1700

Data Index: 4660961 (Open Web Text)

Max Activating Token Index: 261

Text #5

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7636. Min Act: -0.1700

Data Index: 6476383 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7742. Min Act: -0.1700

Data Index: 1241846 (Open Web Text)

Max Activating Token Index: 434

Text #7

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7412. Min Act: -0.1700

Data Index: 814859 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7556. Min Act: -0.1700

Data Index: 4221144 (Open Web Text)

Max Activating Token Index: 645

Text #9

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.6927. Min Act: -0.1700

Data Index: 950384 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7132. Min Act: -0.1700

Data Index: 2295232 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7239. Min Act: -0.1700

Data Index: 5261465 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7000. Min Act: -0.1700

Data Index: 5192414 (Open Web Text)

Max Activating Token Index: 784

Text #13

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7216. Min Act: -0.1700

Data Index: 869780 (Open Web Text)

Max Activating Token Index: 365

Text #14

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7104. Min Act: -0.1700

Data Index: 1772374 (Open Web Text)

Max Activating Token Index: 689

Text #15

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.6926. Min Act: -0.1700

Data Index: 5226491 (Open Web Text)

Max Activating Token Index: 194

Text #16

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.6722. Min Act: -0.1700

Data Index: 5226489 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.6921. Min Act: -0.1700

Data Index: 6347539 (Open Web Text)

Max Activating Token Index: 113

Text #18

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.7096. Min Act: -0.1700

Data Index: 4168287 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.6840. Min Act: -0.1700

Data Index: 4498143 (Open Web Text)

Max Activating Token Index: 45