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

Dataset: Open Web Text

Neuron 2922 in Layer 2

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: 2.1869. Min Range: -2.1869

Max Act: 2.1869. Min Act: -0.1700

Data Index: 2478325 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.1449. Min Act: -0.1700

Data Index: 1475109 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.1544. Min Act: -0.1700

Data Index: 4223700 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.1220. Min Act: -0.1700

Data Index: 6273969 (Open Web Text)

Max Activating Token Index: 599

Text #4

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.1246. Min Act: -0.1700

Data Index: 1993525 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0941. Min Act: -0.1700

Data Index: 8513260 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.1050. Min Act: -0.1700

Data Index: 3141356 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.1023. Min Act: -0.1700

Data Index: 5915131 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0883. Min Act: -0.1700

Data Index: 8189801 (Open Web Text)

Max Activating Token Index: 136

Text #9

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0637. Min Act: -0.1700

Data Index: 6156797 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0581. Min Act: -0.1700

Data Index: 2671620 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0754. Min Act: -0.1700

Data Index: 3211246 (Open Web Text)

Max Activating Token Index: 296

Text #12

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0278. Min Act: -0.1700

Data Index: 1008242 (Open Web Text)

Max Activating Token Index: 981

Text #13

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.9946. Min Act: -0.1700

Data Index: 6880446 (Open Web Text)

Max Activating Token Index: 827

Text #14

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0279. Min Act: -0.1700

Data Index: 6505528 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.9837. Min Act: -0.1700

Data Index: 2035113 (Open Web Text)

Max Activating Token Index: 280

Text #16

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0077. Min Act: -0.1700

Data Index: 7871263 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.9795. Min Act: -0.1700

Data Index: 4671372 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0023. Min Act: -0.1700

Data Index: 7137188 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.0059. Min Act: -0.1700

Data Index: 2608407 (Open Web Text)

Max Activating Token Index: 524