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

Dataset: Open Web Text

Neuron 1928 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: 2.3837. Min Range: -2.3837

Max Act: 2.3837. Min Act: -0.1700

Data Index: 5861765 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.3606. Min Act: -0.1700

Data Index: 2144373 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.3240. Min Act: -0.1700

Data Index: 4576947 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.3115. Min Act: -0.1700

Data Index: 6293374 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2962. Min Act: -0.1700

Data Index: 4518425 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.3094. Min Act: -0.1700

Data Index: 4847339 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2915. Min Act: -0.1700

Data Index: 6070206 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2861. Min Act: -0.1700

Data Index: 3277269 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2886. Min Act: -0.1700

Data Index: 1882293 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2914. Min Act: -0.1700

Data Index: 3243801 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2783. Min Act: -0.1700

Data Index: 6773939 (Open Web Text)

Max Activating Token Index: 528

Text #11

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2761. Min Act: -0.1700

Data Index: 2872597 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2750. Min Act: -0.1700

Data Index: 5165098 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2831. Min Act: -0.1700

Data Index: 4891863 (Open Web Text)

Max Activating Token Index: 478

Text #14

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2791. Min Act: -0.1700

Data Index: 2556905 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2850. Min Act: -0.1700

Data Index: 2120879 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2857. Min Act: -0.1700

Data Index: 1955895 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2842. Min Act: -0.1700

Data Index: 1259834 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2893. Min Act: -0.1700

Data Index: 4558827 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.3837. Min Range: -2.3837

Max Act: 2.2762. Min Act: -0.1700

Data Index: 1118802 (Open Web Text)

Max Activating Token Index: 10