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

Dataset: Open Web Text

Neuron 1648 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: 3.6865. Min Range: -3.6865

Max Act: 3.6737. Min Act: -0.1700

Data Index: 8725472 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6865. Min Act: -0.1700

Data Index: 3757543 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6668. Min Act: -0.1700

Data Index: 6064010 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6685. Min Act: -0.1700

Data Index: 1649617 (Open Web Text)

Max Activating Token Index: 467

Text #4

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6365. Min Act: -0.1700

Data Index: 1028185 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6581. Min Act: -0.1700

Data Index: 2504941 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6460. Min Act: -0.1700

Data Index: 1550578 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6606. Min Act: -0.1700

Data Index: 273724 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6232. Min Act: -0.1700

Data Index: 5875178 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6260. Min Act: -0.1700

Data Index: 5820689 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6260. Min Act: -0.1700

Data Index: 4330591 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6193. Min Act: -0.1700

Data Index: 3850652 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6058. Min Act: -0.1700

Data Index: 2478097 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6260. Min Act: -0.1700

Data Index: 5544512 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6179. Min Act: -0.1700

Data Index: 5305911 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6260. Min Act: -0.1700

Data Index: 1642593 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6260. Min Act: -0.1700

Data Index: 862589 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6260. Min Act: -0.1700

Data Index: 3837839 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6260. Min Act: -0.1700

Data Index: 3804104 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.6865. Min Range: -3.6865

Max Act: 3.6260. Min Act: -0.1700

Data Index: 3595192 (Open Web Text)

Max Activating Token Index: 2