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

Dataset: Open Web Text

Neuron 15 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: 3.0121. Min Range: -3.0121

Max Act: 3.0121. Min Act: -0.1700

Data Index: 3942142 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9732. Min Act: -0.1700

Data Index: 4933637 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9742. Min Act: -0.1700

Data Index: 301809 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9434. Min Act: -0.1700

Data Index: 4563289 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9121. Min Act: -0.1700

Data Index: 2504210 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9198. Min Act: -0.1700

Data Index: 2352409 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9147. Min Act: -0.1700

Data Index: 4004347 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9268. Min Act: -0.1700

Data Index: 3806714 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9069. Min Act: -0.1700

Data Index: 4321782 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9033. Min Act: -0.1700

Data Index: 1913209 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9097. Min Act: -0.1700

Data Index: 6196743 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.8938. Min Act: -0.1700

Data Index: 5975032 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9013. Min Act: -0.1700

Data Index: 5727073 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.8952. Min Act: -0.1700

Data Index: 5656420 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9097. Min Act: -0.1700

Data Index: 2314006 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9021. Min Act: -0.1700

Data Index: 5203484 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.8962. Min Act: -0.1700

Data Index: 2381639 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9014. Min Act: -0.1700

Data Index: 178241 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.8898. Min Act: -0.1700

Data Index: 2075196 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.8854. Min Act: -0.1700

Data Index: 4840906 (Open Web Text)

Max Activating Token Index: 3