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

Dataset: Open Web Text

Neuron 2844 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: 4.7008. Min Range: -4.7008

Max Act: 4.7008. Min Act: -0.1700

Data Index: 7923344 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5778. Min Act: -0.1700

Data Index: 4966768 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5419. Min Act: -0.1700

Data Index: 6954327 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5230. Min Act: -0.1700

Data Index: 8447763 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5270. Min Act: -0.1700

Data Index: 5254855 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5305. Min Act: -0.1700

Data Index: 2013502 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5010. Min Act: -0.1700

Data Index: 5645799 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4850. Min Act: -0.1700

Data Index: 3225575 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5160. Min Act: -0.1700

Data Index: 1056147 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5028. Min Act: -0.1700

Data Index: 2879356 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4965. Min Act: -0.1700

Data Index: 314703 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4985. Min Act: -0.1700

Data Index: 2655024 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.5023. Min Act: -0.1700

Data Index: 5088622 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4761. Min Act: -0.1700

Data Index: 4859622 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4552. Min Act: -0.1700

Data Index: 5707909 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4757. Min Act: -0.1700

Data Index: 1159665 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4412. Min Act: -0.1700

Data Index: 1635551 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4667. Min Act: -0.1700

Data Index: 2016967 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4412. Min Act: -0.1700

Data Index: 229862 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.4480. Min Act: -0.1700

Data Index: 3022390 (Open Web Text)

Max Activating Token Index: 5