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

Dataset: Open Web Text

Neuron 1203 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: 2.9899. Min Range: -2.9899

Max Act: 2.9899. Min Act: -0.1700

Data Index: 8202654 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9582. Min Act: -0.1700

Data Index: 1635233 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9365. Min Act: -0.1700

Data Index: 359276 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9378. Min Act: -0.1700

Data Index: 1999896 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9305. Min Act: -0.1700

Data Index: 7100387 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9272. Min Act: -0.1700

Data Index: 1610117 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9305. Min Act: -0.1700

Data Index: 1804385 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9104. Min Act: -0.1700

Data Index: 1320161 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9127. Min Act: -0.1700

Data Index: 2487093 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9194. Min Act: -0.1700

Data Index: 8793403 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8944. Min Act: -0.1700

Data Index: 7745335 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8888. Min Act: -0.1700

Data Index: 2437938 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.9027. Min Act: -0.1700

Data Index: 2358989 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8894. Min Act: -0.1700

Data Index: 8422991 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8929. Min Act: -0.1700

Data Index: 8403438 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8733. Min Act: -0.1700

Data Index: 6145825 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8778. Min Act: -0.1700

Data Index: 4778341 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8563. Min Act: -0.1700

Data Index: 2168204 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8516. Min Act: -0.1700

Data Index: 7027652 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9899. Min Range: -2.9899

Max Act: 2.8575. Min Act: -0.1700

Data Index: 3914513 (Open Web Text)

Max Activating Token Index: 4