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

Dataset: Open Web Text

Neuron 497 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: 3.6851. Min Range: -3.6851

Max Act: 3.6851. Min Act: -0.1700

Data Index: 4372427 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6733. Min Act: -0.1700

Data Index: 4527175 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6769. Min Act: -0.1700

Data Index: 7699308 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6224. Min Act: -0.1700

Data Index: 7994833 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6107. Min Act: -0.1700

Data Index: 3409292 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5699. Min Act: -0.1700

Data Index: 7774703 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5520. Min Act: -0.1700

Data Index: 4973397 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5494. Min Act: -0.1700

Data Index: 5229265 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5563. Min Act: -0.1700

Data Index: 8644569 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5677. Min Act: -0.1700

Data Index: 1470225 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5449. Min Act: -0.1700

Data Index: 2638345 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5392. Min Act: -0.1700

Data Index: 1364432 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5468. Min Act: -0.1700

Data Index: 4608565 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5652. Min Act: -0.1700

Data Index: 538581 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5503. Min Act: -0.1700

Data Index: 6307849 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5536. Min Act: -0.1700

Data Index: 2967727 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5689. Min Act: -0.1700

Data Index: 2701426 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5243. Min Act: -0.1700

Data Index: 5055392 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5229. Min Act: -0.1700

Data Index: 1220496 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5228. Min Act: -0.1700

Data Index: 3702591 (Open Web Text)

Max Activating Token Index: 8