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

Dataset: Open Web Text

Neuron 2956 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: 4.8090. Min Range: -4.8090

Max Act: 4.8090. Min Act: -0.1700

Data Index: 770224 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.6335. Min Act: -0.1700

Data Index: 2758716 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.6442. Min Act: -0.1700

Data Index: 7669282 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.6156. Min Act: -0.1700

Data Index: 2862310 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5731. Min Act: -0.1700

Data Index: 7433437 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5844. Min Act: -0.1700

Data Index: 6665936 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5805. Min Act: -0.1700

Data Index: 5736026 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5487. Min Act: -0.1700

Data Index: 6099927 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5269. Min Act: -0.1700

Data Index: 4986954 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5552. Min Act: -0.1700

Data Index: 2404027 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5381. Min Act: -0.1700

Data Index: 868585 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5431. Min Act: -0.1700

Data Index: 4272787 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.4954. Min Act: -0.1700

Data Index: 2522964 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5000. Min Act: -0.1700

Data Index: 4564104 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5111. Min Act: -0.1700

Data Index: 3207236 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5284. Min Act: -0.1700

Data Index: 8208512 (Open Web Text)

Max Activating Token Index: 28

Text #16

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.5077. Min Act: -0.1700

Data Index: 5964310 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.4926. Min Act: -0.1700

Data Index: 2822689 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.4708. Min Act: -0.1700

Data Index: 772610 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 4.8090. Min Range: -4.8090

Max Act: 4.4759. Min Act: -0.1700

Data Index: 5313823 (Open Web Text)

Max Activating Token Index: 6