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

Dataset: Open Web Text

Neuron 1483 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: 2.5804. Min Range: -2.5804

Max Act: 2.5681. Min Act: -0.1700

Data Index: 4671609 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.5804. Min Act: -0.1700

Data Index: 4380511 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.5128. Min Act: -0.1700

Data Index: 4828802 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.5118. Min Act: -0.1700

Data Index: 2211721 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4681. Min Act: -0.1700

Data Index: 8417156 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4770. Min Act: -0.1700

Data Index: 7037279 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4894. Min Act: -0.1700

Data Index: 6656921 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4817. Min Act: -0.1700

Data Index: 6861069 (Open Web Text)

Max Activating Token Index: 202

Text #8

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4695. Min Act: -0.1700

Data Index: 7273647 (Open Web Text)

Max Activating Token Index: 127

Text #9

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4804. Min Act: -0.1700

Data Index: 2542514 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4665. Min Act: -0.1700

Data Index: 4004986 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4728. Min Act: -0.1700

Data Index: 3610624 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4633. Min Act: -0.1700

Data Index: 8753181 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4737. Min Act: -0.1700

Data Index: 2932570 (Open Web Text)

Max Activating Token Index: 176

Text #14

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4648. Min Act: -0.1700

Data Index: 7648531 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4620. Min Act: -0.1700

Data Index: 3565984 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4616. Min Act: -0.1700

Data Index: 2163802 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4468. Min Act: -0.1700

Data Index: 3650974 (Open Web Text)

Max Activating Token Index: 119

Text #18

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4497. Min Act: -0.1700

Data Index: 376369 (Open Web Text)

Max Activating Token Index: 637

Text #19

Max Range: 2.5804. Min Range: -2.5804

Max Act: 2.4618. Min Act: -0.1700

Data Index: 2081721 (Open Web Text)

Max Activating Token Index: 641