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

Dataset: Open Web Text

Neuron 3024 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: 2.7754. Min Range: -2.7754

Max Act: 2.7730. Min Act: -0.1700

Data Index: 8184802 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7754. Min Act: -0.1700

Data Index: 1966501 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7589. Min Act: -0.1700

Data Index: 6609177 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7569. Min Act: -0.1700

Data Index: 4269633 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7424. Min Act: -0.1700

Data Index: 3774526 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7159. Min Act: -0.1700

Data Index: 4324261 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7155. Min Act: -0.1700

Data Index: 8128668 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7251. Min Act: -0.1700

Data Index: 442662 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7211. Min Act: -0.1700

Data Index: 7804879 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7050. Min Act: -0.1700

Data Index: 236570 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7004. Min Act: -0.1700

Data Index: 444455 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.7175. Min Act: -0.1700

Data Index: 7984443 (Open Web Text)

Max Activating Token Index: 772

Text #12

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.6826. Min Act: -0.1700

Data Index: 2229742 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.6900. Min Act: -0.1700

Data Index: 5472742 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.6885. Min Act: -0.1700

Data Index: 3372949 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.6816. Min Act: -0.1700

Data Index: 522973 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.6872. Min Act: -0.1700

Data Index: 1769805 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.6855. Min Act: -0.1700

Data Index: 4583203 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.6893. Min Act: -0.1700

Data Index: 371239 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.7754. Min Range: -2.7754

Max Act: 2.6917. Min Act: -0.1700

Data Index: 1604160 (Open Web Text)

Max Activating Token Index: 3