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

Dataset: Open Web Text

Neuron 2455 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: 0.5984. Min Range: -0.5984

Max Act: 0.5984. Min Act: -0.1613

Data Index: 6739941 (Open Web Text)

Max Activating Token Index: 60

Text #1

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5879. Min Act: -0.1597

Data Index: 2567826 (Open Web Text)

Max Activating Token Index: 51

Text #2

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5892. Min Act: -0.1550

Data Index: 6268995 (Open Web Text)

Max Activating Token Index: 48

Text #3

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5887. Min Act: -0.1578

Data Index: 4758988 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5821. Min Act: -0.1582

Data Index: 5632599 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5868. Min Act: -0.1486

Data Index: 7376144 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5802. Min Act: -0.1536

Data Index: 7101148 (Open Web Text)

Max Activating Token Index: 903

Text #7

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5801. Min Act: -0.1587

Data Index: 368523 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5703. Min Act: -0.1360

Data Index: 3309016 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5732. Min Act: -0.1601

Data Index: 367758 (Open Web Text)

Max Activating Token Index: 48

Text #10

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5729. Min Act: -0.1676

Data Index: 6579496 (Open Web Text)

Max Activating Token Index: 47

Text #11

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5718. Min Act: -0.1678

Data Index: 3333969 (Open Web Text)

Max Activating Token Index: 45

Text #12

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5756. Min Act: -0.1563

Data Index: 8226650 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5717. Min Act: -0.1468

Data Index: 8507425 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5690. Min Act: -0.1616

Data Index: 6409915 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5707. Min Act: -0.1653

Data Index: 8520309 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5677. Min Act: -0.1692

Data Index: 270001 (Open Web Text)

Max Activating Token Index: 53

Text #17

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5679. Min Act: -0.1648

Data Index: 2883041 (Open Web Text)

Max Activating Token Index: 50

Text #18

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5711. Min Act: -0.1602

Data Index: 2671976 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5685. Min Act: -0.1667

Data Index: 344877 (Open Web Text)

Max Activating Token Index: 50