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

Dataset: Open Web Text

Neuron 502 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: 1.7894. Min Range: -1.7894

Max Act: 1.7894. Min Act: -0.1700

Data Index: 4757744 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.7697. Min Act: -0.1700

Data Index: 4944934 (Open Web Text)

Max Activating Token Index: 533

Text #2

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.7410. Min Act: -0.1700

Data Index: 1654795 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.7525. Min Act: -0.1700

Data Index: 7244233 (Open Web Text)

Max Activating Token Index: 619

Text #4

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.7311. Min Act: -0.1700

Data Index: 3535461 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.7010. Min Act: -0.1700

Data Index: 4521889 (Open Web Text)

Max Activating Token Index: 62

Text #6

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6991. Min Act: -0.1700

Data Index: 1161508 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6906. Min Act: -0.1700

Data Index: 7887759 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6896. Min Act: -0.1700

Data Index: 2017373 (Open Web Text)

Max Activating Token Index: 99

Text #9

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6888. Min Act: -0.1700

Data Index: 4163304 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6789. Min Act: -0.1700

Data Index: 5195942 (Open Web Text)

Max Activating Token Index: 213

Text #11

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6643. Min Act: -0.1700

Data Index: 2907423 (Open Web Text)

Max Activating Token Index: 52

Text #12

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6710. Min Act: -0.1700

Data Index: 2951032 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6641. Min Act: -0.1700

Data Index: 5895602 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6580. Min Act: -0.1700

Data Index: 6486765 (Open Web Text)

Max Activating Token Index: 39

Text #15

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6690. Min Act: -0.1697

Data Index: 8697525 (Open Web Text)

Max Activating Token Index: 670

Text #16

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6571. Min Act: -0.1700

Data Index: 3836475 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6543. Min Act: -0.1700

Data Index: 3742185 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6620. Min Act: -0.1700

Data Index: 7958139 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.6615. Min Act: -0.1700

Data Index: 6270227 (Open Web Text)

Max Activating Token Index: 501