Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 4608 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.9952. Min Act: -0.1700

Data Index: 2514856 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.9952. Min Act: -0.1700

Data Index: 8664932 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.9327. Min Act: -0.1700

Data Index: 7197206 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.9014. Min Act: -0.1700

Data Index: 3495821 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.9014. Min Act: -0.1698

Data Index: 1631921 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8702. Min Act: -0.1700

Data Index: 3454522 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8702. Min Act: -0.1698

Data Index: 51925 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8702. Min Act: -0.1700

Data Index: 5184465 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1699

Data Index: 31314 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1700

Data Index: 157374 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1697

Data Index: 156207 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1700

Data Index: 362730 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1700

Data Index: 504784 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1699

Data Index: 602412 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1700

Data Index: 553780 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1700

Data Index: 192763 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8077. Min Act: -0.1700

Data Index: 406224 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1700

Data Index: 290972 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1700

Data Index: 394805 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 5.9952. Min Range: -5.9952

Max Act: 5.8389. Min Act: -0.1697

Data Index: 191645 (Open Web Text)

Max Activating Token Index: 1