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

Dataset: Open Web Text

Neuron 247 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: 4.5022. Min Range: -4.5022

Max Act: 4.5022. Min Act: -0.1700

Data Index: 6955428 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.4723. Min Act: -0.1700

Data Index: 6383793 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.3759. Min Act: -0.1700

Data Index: 1462047 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.4032. Min Act: -0.1700

Data Index: 4664907 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.3811. Min Act: -0.1700

Data Index: 2246934 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.3636. Min Act: -0.1700

Data Index: 7027041 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.3677. Min Act: -0.1700

Data Index: 3387487 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.3762. Min Act: -0.1700

Data Index: 2085579 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.3219. Min Act: -0.1700

Data Index: 6964052 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.3068. Min Act: -0.1700

Data Index: 5481216 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.3119. Min Act: -0.1700

Data Index: 5118132 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2736. Min Act: -0.1700

Data Index: 7823122 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2748. Min Act: -0.1700

Data Index: 391451 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2839. Min Act: -0.1700

Data Index: 2596767 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2700. Min Act: -0.1700

Data Index: 1097019 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2595. Min Act: -0.1700

Data Index: 3075707 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2551. Min Act: -0.1700

Data Index: 2229033 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2677. Min Act: -0.1700

Data Index: 7651681 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2416. Min Act: -0.1700

Data Index: 7695329 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.5022. Min Range: -4.5022

Max Act: 4.2672. Min Act: -0.1700

Data Index: 341382 (Open Web Text)

Max Activating Token Index: 4