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

Dataset: Open Web Text

Neuron 1901 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: 2.9149. Min Range: -2.9149

Max Act: 2.9051. Min Act: -0.1700

Data Index: 6840822 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.9149. Min Act: -0.1700

Data Index: 2324115 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8962. Min Act: -0.1700

Data Index: 2606891 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8870. Min Act: -0.1700

Data Index: 7083209 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8773. Min Act: -0.1700

Data Index: 5117770 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8398. Min Act: -0.1700

Data Index: 7333804 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8518. Min Act: -0.1700

Data Index: 945101 (Open Web Text)

Max Activating Token Index: 775

Text #7

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8223. Min Act: -0.1700

Data Index: 8637278 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8358. Min Act: -0.1700

Data Index: 1486353 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8234. Min Act: -0.1700

Data Index: 1184807 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8250. Min Act: -0.1700

Data Index: 4981330 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8095. Min Act: -0.1700

Data Index: 1400393 (Open Web Text)

Max Activating Token Index: 548

Text #12

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8192. Min Act: -0.1700

Data Index: 3582377 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8047. Min Act: -0.1700

Data Index: 324512 (Open Web Text)

Max Activating Token Index: 478

Text #14

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8143. Min Act: -0.1700

Data Index: 3974190 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8101. Min Act: -0.1700

Data Index: 5847516 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8150. Min Act: -0.1700

Data Index: 5792131 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8192. Min Act: -0.1700

Data Index: 2893947 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8183. Min Act: -0.1700

Data Index: 5573474 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.9149. Min Range: -2.9149

Max Act: 2.8090. Min Act: -0.1700

Data Index: 1711499 (Open Web Text)

Max Activating Token Index: 5