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

Dataset: Open Web Text

Neuron 1326 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: 2.9735. Min Range: -2.9735

Max Act: 2.9735. Min Act: -0.1700

Data Index: 8639352 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.9474. Min Act: -0.1700

Data Index: 6490734 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.9072. Min Act: -0.1700

Data Index: 8163545 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.9026. Min Act: -0.1700

Data Index: 8310364 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.9053. Min Act: -0.1700

Data Index: 3079352 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8954. Min Act: -0.1700

Data Index: 4151495 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8841. Min Act: -0.1700

Data Index: 2349485 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8765. Min Act: -0.1700

Data Index: 3150690 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8665. Min Act: -0.1700

Data Index: 2604487 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8637. Min Act: -0.1700

Data Index: 1861750 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8609. Min Act: -0.1700

Data Index: 1890300 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8612. Min Act: -0.1700

Data Index: 1891296 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8529. Min Act: -0.1700

Data Index: 4276902 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8625. Min Act: -0.1700

Data Index: 1262730 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8386. Min Act: -0.1700

Data Index: 6997343 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8469. Min Act: -0.1700

Data Index: 6926446 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8342. Min Act: -0.1700

Data Index: 8434852 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8482. Min Act: -0.1700

Data Index: 5945052 (Open Web Text)

Max Activating Token Index: 959

Text #18

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8463. Min Act: -0.1700

Data Index: 3908350 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 2.9735. Min Range: -2.9735

Max Act: 2.8407. Min Act: -0.1700

Data Index: 2463060 (Open Web Text)

Max Activating Token Index: 12