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

Dataset: Open Web Text

Neuron 2418 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: 3.7836. Min Range: -3.7836

Max Act: 3.7836. Min Act: -0.1700

Data Index: 3136954 (Open Web Text)

Max Activating Token Index: 490

Text #1

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.7590. Min Act: -0.1700

Data Index: 6523026 (Open Web Text)

Max Activating Token Index: 796

Text #2

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.7421. Min Act: -0.1700

Data Index: 2299096 (Open Web Text)

Max Activating Token Index: 708

Text #3

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.7075. Min Act: -0.1700

Data Index: 5812167 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.7051. Min Act: -0.1700

Data Index: 5066105 (Open Web Text)

Max Activating Token Index: 248

Text #5

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.7261. Min Act: -0.1700

Data Index: 2168072 (Open Web Text)

Max Activating Token Index: 753

Text #6

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6513. Min Act: -0.1700

Data Index: 1900432 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6980. Min Act: -0.1700

Data Index: 1940420 (Open Web Text)

Max Activating Token Index: 931

Text #8

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6906. Min Act: -0.1700

Data Index: 7055832 (Open Web Text)

Max Activating Token Index: 707

Text #9

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6762. Min Act: -0.1700

Data Index: 6395228 (Open Web Text)

Max Activating Token Index: 371

Text #10

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6523. Min Act: -0.1700

Data Index: 2399992 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6587. Min Act: -0.1700

Data Index: 5274011 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6631. Min Act: -0.1700

Data Index: 542184 (Open Web Text)

Max Activating Token Index: 90

Text #13

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.5929. Min Act: -0.1700

Data Index: 8361017 (Open Web Text)

Max Activating Token Index: 141

Text #14

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6080. Min Act: -0.1700

Data Index: 4909983 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.6133. Min Act: -0.1700

Data Index: 993975 (Open Web Text)

Max Activating Token Index: 411

Text #16

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.5937. Min Act: -0.1700

Data Index: 3457805 (Open Web Text)

Max Activating Token Index: 775

Text #17

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.5743. Min Act: -0.1700

Data Index: 1041838 (Open Web Text)

Max Activating Token Index: 549

Text #18

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.5733. Min Act: -0.1700

Data Index: 1887625 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 3.7836. Min Range: -3.7836

Max Act: 3.5897. Min Act: -0.1700

Data Index: 4464581 (Open Web Text)

Max Activating Token Index: 161