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

Dataset: Open Web Text

Neuron 2951 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: 3.2623. Min Range: -3.2623

Max Act: 3.2623. Min Act: -0.1700

Data Index: 2318272 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.2355. Min Act: -0.1700

Data Index: 4958700 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.2159. Min Act: -0.1700

Data Index: 2306645 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1747. Min Act: -0.1700

Data Index: 4332005 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1479. Min Act: -0.1700

Data Index: 5685357 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1449. Min Act: -0.1700

Data Index: 6040541 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1294. Min Act: -0.1700

Data Index: 6756912 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1183. Min Act: -0.1700

Data Index: 7718757 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1245. Min Act: -0.1700

Data Index: 3657340 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1289. Min Act: -0.1700

Data Index: 6752201 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1195. Min Act: -0.1700

Data Index: 857087 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1080. Min Act: -0.1700

Data Index: 4296419 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.1060. Min Act: -0.1700

Data Index: 1971863 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.0865. Min Act: -0.1700

Data Index: 1543487 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.0895. Min Act: -0.1700

Data Index: 2930146 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.0865. Min Act: -0.1700

Data Index: 3499889 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.0920. Min Act: -0.1700

Data Index: 3526158 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.0865. Min Act: -0.1700

Data Index: 1609172 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.0865. Min Act: -0.1700

Data Index: 1072752 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.2623. Min Range: -3.2623

Max Act: 3.0865. Min Act: -0.1700

Data Index: 1431948 (Open Web Text)

Max Activating Token Index: 3