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

Dataset: Open Web Text

Neuron 2816 in Layer 4

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: 3.7023. Min Range: -3.7023

Max Act: 3.6991. Min Act: -0.1700

Data Index: 8802164 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.7023. Min Act: -0.1700

Data Index: 228028 (Open Web Text)

Max Activating Token Index: 228

Text #2

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.6518. Min Act: -0.1700

Data Index: 6662945 (Open Web Text)

Max Activating Token Index: 930

Text #3

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.6738. Min Act: -0.1700

Data Index: 6151917 (Open Web Text)

Max Activating Token Index: 950

Text #4

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.6016. Min Act: -0.1700

Data Index: 2012682 (Open Web Text)

Max Activating Token Index: 840

Text #5

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.6152. Min Act: -0.1700

Data Index: 3168744 (Open Web Text)

Max Activating Token Index: 354

Text #6

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5927. Min Act: -0.1700

Data Index: 8211936 (Open Web Text)

Max Activating Token Index: 551

Text #7

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5926. Min Act: -0.1700

Data Index: 5881089 (Open Web Text)

Max Activating Token Index: 162

Text #8

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5803. Min Act: -0.1700

Data Index: 3520898 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.6064. Min Act: -0.1700

Data Index: 5732047 (Open Web Text)

Max Activating Token Index: 705

Text #10

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5487. Min Act: -0.1700

Data Index: 667362 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5359. Min Act: -0.1700

Data Index: 3258516 (Open Web Text)

Max Activating Token Index: 895

Text #12

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5369. Min Act: -0.1700

Data Index: 4048260 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5193. Min Act: -0.1700

Data Index: 8244013 (Open Web Text)

Max Activating Token Index: 408

Text #14

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5195. Min Act: -0.1700

Data Index: 4821725 (Open Web Text)

Max Activating Token Index: 284

Text #15

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5205. Min Act: -0.1700

Data Index: 3126333 (Open Web Text)

Max Activating Token Index: 887

Text #16

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5357. Min Act: -0.1700

Data Index: 4577839 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.4897. Min Act: -0.1700

Data Index: 4043527 (Open Web Text)

Max Activating Token Index: 781

Text #18

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5257. Min Act: -0.1700

Data Index: 7446669 (Open Web Text)

Max Activating Token Index: 657

Text #19

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5535. Min Act: -0.1700

Data Index: 195830 (Open Web Text)

Max Activating Token Index: 251