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

Dataset: Open Web Text

Neuron 611 in Layer 3

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: 4.7571. Min Range: -4.7571

Max Act: 4.7571. Min Act: -0.1700

Data Index: 7156273 (Open Web Text)

Max Activating Token Index: 296

Text #1

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.7342. Min Act: -0.1700

Data Index: 2225032 (Open Web Text)

Max Activating Token Index: 307

Text #2

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.7187. Min Act: -0.1700

Data Index: 5008295 (Open Web Text)

Max Activating Token Index: 634

Text #3

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6662. Min Act: -0.1700

Data Index: 5475285 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6836. Min Act: -0.1700

Data Index: 7128283 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.7106. Min Act: -0.1700

Data Index: 1025167 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6486. Min Act: -0.1700

Data Index: 7479071 (Open Web Text)

Max Activating Token Index: 794

Text #7

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6590. Min Act: -0.1700

Data Index: 5178214 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6392. Min Act: -0.1700

Data Index: 8672436 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6543. Min Act: -0.1700

Data Index: 3638985 (Open Web Text)

Max Activating Token Index: 812

Text #10

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6051. Min Act: -0.1700

Data Index: 7508086 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6282. Min Act: -0.1700

Data Index: 3003922 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6217. Min Act: -0.1700

Data Index: 8760382 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6010. Min Act: -0.1700

Data Index: 1466344 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.5783. Min Act: -0.1700

Data Index: 8179901 (Open Web Text)

Max Activating Token Index: 1018

Text #15

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6286. Min Act: -0.1700

Data Index: 1459738 (Open Web Text)

Max Activating Token Index: 549

Text #16

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6131. Min Act: -0.1700

Data Index: 3128538 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6410. Min Act: -0.1700

Data Index: 8642610 (Open Web Text)

Max Activating Token Index: 807

Text #18

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6014. Min Act: -0.1700

Data Index: 1149348 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.7571. Min Range: -4.7571

Max Act: 4.6018. Min Act: -0.1700

Data Index: 7154552 (Open Web Text)

Max Activating Token Index: 837