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

Dataset: Open Web Text

Neuron 1511 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: 3.6684. Min Range: -3.6684

Max Act: 3.6684. Min Act: -0.1700

Data Index: 6833385 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6308. Min Act: -0.1700

Data Index: 6146409 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6548. Min Act: -0.1700

Data Index: 2336105 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6107. Min Act: -0.1700

Data Index: 4078291 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6162. Min Act: -0.1700

Data Index: 4834911 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6117. Min Act: -0.1700

Data Index: 4657255 (Open Web Text)

Max Activating Token Index: 828

Text #6

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6256. Min Act: -0.1700

Data Index: 2229620 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6127. Min Act: -0.1700

Data Index: 8580561 (Open Web Text)

Max Activating Token Index: 835

Text #8

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6209. Min Act: -0.1700

Data Index: 8039048 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6154. Min Act: -0.1700

Data Index: 994061 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6142. Min Act: -0.1700

Data Index: 7714115 (Open Web Text)

Max Activating Token Index: 886

Text #11

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5776. Min Act: -0.1700

Data Index: 2902410 (Open Web Text)

Max Activating Token Index: 1017

Text #12

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5743. Min Act: -0.1700

Data Index: 2972508 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6023. Min Act: -0.1700

Data Index: 3132395 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5606. Min Act: -0.1700

Data Index: 2850588 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5774. Min Act: -0.1700

Data Index: 5427 (Open Web Text)

Max Activating Token Index: 939

Text #16

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5741. Min Act: -0.1700

Data Index: 6564675 (Open Web Text)

Max Activating Token Index: 824

Text #17

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5941. Min Act: -0.1700

Data Index: 6783032 (Open Web Text)

Max Activating Token Index: 938

Text #18

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5799. Min Act: -0.1700

Data Index: 1710262 (Open Web Text)

Max Activating Token Index: 39

Text #19

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5853. Min Act: -0.1700

Data Index: 1950156 (Open Web Text)

Max Activating Token Index: 1011