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

Dataset: Open Web Text

Neuron 876 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: 1.8130. Min Range: -1.8130

Max Act: 1.8130. Min Act: -0.1607

Data Index: 6171333 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7597. Min Act: -0.1607

Data Index: 4043860 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7323. Min Act: -0.1607

Data Index: 3684735 (Open Web Text)

Max Activating Token Index: 591

Text #3

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7183. Min Act: -0.1607

Data Index: 5061690 (Open Web Text)

Max Activating Token Index: 851

Text #4

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7155. Min Act: -0.1607

Data Index: 5943284 (Open Web Text)

Max Activating Token Index: 380

Text #5

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7164. Min Act: -0.1607

Data Index: 2483452 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7052. Min Act: -0.1607

Data Index: 4790940 (Open Web Text)

Max Activating Token Index: 915

Text #7

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7082. Min Act: -0.1607

Data Index: 6014018 (Open Web Text)

Max Activating Token Index: 409

Text #8

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.6980. Min Act: -0.1607

Data Index: 1950240 (Open Web Text)

Max Activating Token Index: 721

Text #9

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7039. Min Act: -0.1607

Data Index: 5166449 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7060. Min Act: -0.1607

Data Index: 5432380 (Open Web Text)

Max Activating Token Index: 362

Text #11

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7058. Min Act: -0.1607

Data Index: 1188241 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.6919. Min Act: -0.1607

Data Index: 5186223 (Open Web Text)

Max Activating Token Index: 597

Text #13

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.6831. Min Act: -0.1607

Data Index: 2630327 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7025. Min Act: -0.1607

Data Index: 179815 (Open Web Text)

Max Activating Token Index: 518

Text #15

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.7029. Min Act: -0.1607

Data Index: 5567959 (Open Web Text)

Max Activating Token Index: 962

Text #16

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.6929. Min Act: -0.1607

Data Index: 6014016 (Open Web Text)

Max Activating Token Index: 527

Text #17

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.6954. Min Act: -0.1607

Data Index: 2156459 (Open Web Text)

Max Activating Token Index: 812

Text #18

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.6910. Min Act: -0.1607

Data Index: 552388 (Open Web Text)

Max Activating Token Index: 150

Text #19

Max Range: 1.8130. Min Range: -1.8130

Max Act: 1.6927. Min Act: -0.1607

Data Index: 4866905 (Open Web Text)

Max Activating Token Index: 963