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

Dataset: Open Web Text

Neuron 3616 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.1038. Min Act: -0.1700

Data Index: 5727558 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.1038. Min Act: -0.1700

Data Index: 6532059 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.1038. Min Act: -0.1700

Data Index: 2972549 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.1038. Min Act: -0.1700

Data Index: 324620 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0413. Min Act: -0.1700

Data Index: 6646918 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0413. Min Act: -0.1700

Data Index: 3737478 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0726. Min Act: -0.1700

Data Index: 3655680 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0413. Min Act: -0.1700

Data Index: 15639 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0101. Min Act: -0.1700

Data Index: 1823669 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0101. Min Act: -0.1700

Data Index: 2812429 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0101. Min Act: -0.1700

Data Index: 8041399 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0101. Min Act: -0.1700

Data Index: 7793585 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9788. Min Act: -0.1700

Data Index: 7205222 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0101. Min Act: -0.1700

Data Index: 6902779 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0413. Min Act: -0.1700

Data Index: 3407998 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 5.1038. Min Range: -5.1038

Max Act: 5.0101. Min Act: -0.1700

Data Index: 558165 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9788. Min Act: -0.1700

Data Index: 1120179 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9788. Min Act: -0.1700

Data Index: 1799377 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9788. Min Act: -0.1700

Data Index: 2877187 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 5.1038. Min Range: -5.1038

Max Act: 4.9788. Min Act: -0.1700

Data Index: 2898038 (Open Web Text)

Max Activating Token Index: 2