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

Dataset: Open Web Text

Neuron 740 in Layer 0

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: 4.2782. Min Range: -4.2782

Max Act: 4.2782. Min Act: -0.1700

Data Index: 6495338 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2591. Min Act: -0.1700

Data Index: 4597844 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2487. Min Act: -0.1700

Data Index: 4147822 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2422. Min Act: -0.1700

Data Index: 7168818 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2261. Min Act: -0.1700

Data Index: 6339295 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2373. Min Act: -0.1700

Data Index: 615109 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2331. Min Act: -0.1700

Data Index: 577794 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1864. Min Act: -0.1700

Data Index: 6580325 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1911. Min Act: -0.1700

Data Index: 6233972 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1913. Min Act: -0.1700

Data Index: 2049075 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1913. Min Act: -0.1700

Data Index: 8552803 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1749. Min Act: -0.1700

Data Index: 7089674 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1621. Min Act: -0.1700

Data Index: 6917078 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1782. Min Act: -0.1700

Data Index: 4390733 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1653. Min Act: -0.1700

Data Index: 7417535 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1495. Min Act: -0.1700

Data Index: 8178527 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1582. Min Act: -0.1700

Data Index: 489198 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1748. Min Act: -0.1700

Data Index: 8215711 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1754. Min Act: -0.1700

Data Index: 5032059 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1813. Min Act: -0.1700

Data Index: 2754362 (Open Web Text)

Max Activating Token Index: 5