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

Dataset: Open Web Text

Neuron 1645 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: 4.6782. Min Range: -4.6782

Max Act: 4.6782. Min Act: -0.1700

Data Index: 5907329 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.6513. Min Act: -0.1700

Data Index: 191305 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.6761. Min Act: -0.1700

Data Index: 344961 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.6715. Min Act: -0.1700

Data Index: 462041 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.6235. Min Act: -0.1700

Data Index: 2989063 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5980. Min Act: -0.1700

Data Index: 6165515 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5660. Min Act: -0.1700

Data Index: 6305993 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5734. Min Act: -0.1700

Data Index: 6494483 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5581. Min Act: -0.1700

Data Index: 6801875 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5554. Min Act: -0.1700

Data Index: 6938501 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5540. Min Act: -0.1700

Data Index: 2445989 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5721. Min Act: -0.1700

Data Index: 7089131 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5730. Min Act: -0.1700

Data Index: 3288883 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5785. Min Act: -0.1700

Data Index: 5049761 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5626. Min Act: -0.1700

Data Index: 7091681 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5683. Min Act: -0.1700

Data Index: 5478698 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5582. Min Act: -0.1700

Data Index: 383277 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5795. Min Act: -0.1700

Data Index: 7505960 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5597. Min Act: -0.1700

Data Index: 7671964 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.6782. Min Range: -4.6782

Max Act: 4.5541. Min Act: -0.1700

Data Index: 8277934 (Open Web Text)

Max Activating Token Index: 6