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

Dataset: Open Web Text

Neuron 291 in Layer 1

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: 1.2732. Min Range: -1.2732

Max Act: 1.2732. Min Act: -0.1700

Data Index: 7752678 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.2477. Min Act: -0.1699

Data Index: 4069905 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.2457. Min Act: -0.1700

Data Index: 4584564 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.2264. Min Act: -0.1700

Data Index: 5943607 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1962. Min Act: -0.1700

Data Index: 7721868 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1966. Min Act: -0.1699

Data Index: 3281493 (Open Web Text)

Max Activating Token Index: 234

Text #6

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.2039. Min Act: -0.1700

Data Index: 2692022 (Open Web Text)

Max Activating Token Index: 836

Text #7

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1912. Min Act: -0.1699

Data Index: 7755617 (Open Web Text)

Max Activating Token Index: 683

Text #8

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1914. Min Act: -0.1699

Data Index: 6770062 (Open Web Text)

Max Activating Token Index: 933

Text #9

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1736. Min Act: -0.1700

Data Index: 390713 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1799. Min Act: -0.1700

Data Index: 848498 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1888. Min Act: -0.1699

Data Index: 6932049 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1723. Min Act: -0.1695

Data Index: 4147807 (Open Web Text)

Max Activating Token Index: 331

Text #13

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1710. Min Act: -0.1679

Data Index: 881214 (Open Web Text)

Max Activating Token Index: 440

Text #14

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1773. Min Act: -0.1700

Data Index: 4183563 (Open Web Text)

Max Activating Token Index: 294

Text #15

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1696. Min Act: -0.1700

Data Index: 5807613 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1636. Min Act: -0.1700

Data Index: 7875652 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1683. Min Act: -0.1700

Data Index: 8286081 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1624. Min Act: -0.1700

Data Index: 6887671 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1602. Min Act: -0.1700

Data Index: 7162387 (Open Web Text)

Max Activating Token Index: 10