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

Dataset: Open Web Text

Neuron 844 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: 3.1754. Min Range: -3.1754

Max Act: 3.1754. Min Act: -0.1700

Data Index: 5959892 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.1149. Min Act: -0.1700

Data Index: 3817645 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.1081. Min Act: -0.1700

Data Index: 3857551 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0885. Min Act: -0.1700

Data Index: 6177892 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0813. Min Act: -0.1700

Data Index: 1767752 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0698. Min Act: -0.1700

Data Index: 2197322 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0617. Min Act: -0.1700

Data Index: 3730143 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0500. Min Act: -0.1700

Data Index: 5561993 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0579. Min Act: -0.1700

Data Index: 2199503 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0418. Min Act: -0.1700

Data Index: 7400669 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0285. Min Act: -0.1700

Data Index: 2002871 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0253. Min Act: -0.1700

Data Index: 4917505 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0224. Min Act: -0.1700

Data Index: 4150711 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0225. Min Act: -0.1700

Data Index: 4737185 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0165. Min Act: -0.1700

Data Index: 510111 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0160. Min Act: -0.1700

Data Index: 2037708 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0170. Min Act: -0.1700

Data Index: 4575520 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0151. Min Act: -0.1700

Data Index: 8194722 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0297. Min Act: -0.1700

Data Index: 4008529 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.0229. Min Act: -0.1700

Data Index: 3962255 (Open Web Text)

Max Activating Token Index: 3