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

Dataset: Open Web Text

Neuron 273 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: 3.8490. Min Range: -3.8490

Max Act: 3.8490. Min Act: -0.1700

Data Index: 884122 (Open Web Text)

Max Activating Token Index: 116

Text #1

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.6546. Min Act: -0.1700

Data Index: 6951878 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5707. Min Act: -0.1700

Data Index: 7093031 (Open Web Text)

Max Activating Token Index: 307

Text #3

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.6149. Min Act: -0.1700

Data Index: 5148981 (Open Web Text)

Max Activating Token Index: 1010

Text #4

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.6037. Min Act: -0.1700

Data Index: 2563454 (Open Web Text)

Max Activating Token Index: 242

Text #5

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5836. Min Act: -0.1700

Data Index: 6936714 (Open Web Text)

Max Activating Token Index: 806

Text #6

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5976. Min Act: -0.1700

Data Index: 1417770 (Open Web Text)

Max Activating Token Index: 638

Text #7

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5729. Min Act: -0.1700

Data Index: 6683739 (Open Web Text)

Max Activating Token Index: 550

Text #8

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5583. Min Act: -0.1700

Data Index: 7281969 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5600. Min Act: -0.1700

Data Index: 31259 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5718. Min Act: -0.1700

Data Index: 3374913 (Open Web Text)

Max Activating Token Index: 1013

Text #11

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5363. Min Act: -0.1700

Data Index: 3287308 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5053. Min Act: -0.1700

Data Index: 1911941 (Open Web Text)

Max Activating Token Index: 794

Text #13

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4819. Min Act: -0.1700

Data Index: 4887225 (Open Web Text)

Max Activating Token Index: 576

Text #14

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4780. Min Act: -0.1700

Data Index: 7629617 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4889. Min Act: -0.1700

Data Index: 6948755 (Open Web Text)

Max Activating Token Index: 444

Text #16

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4631. Min Act: -0.1700

Data Index: 613315 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4697. Min Act: -0.1700

Data Index: 311074 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4683. Min Act: -0.1700

Data Index: 5784093 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4812. Min Act: -0.1700

Data Index: 916430 (Open Web Text)

Max Activating Token Index: 982