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

Dataset: Open Web Text

Neuron 763 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: 4.8824. Min Range: -4.8824

Max Act: 4.8824. Min Act: -0.1700

Data Index: 1243942 (Open Web Text)

Max Activating Token Index: 508

Text #1

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.8367. Min Act: -0.1700

Data Index: 6451374 (Open Web Text)

Max Activating Token Index: 948

Text #2

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.8004. Min Act: -0.1700

Data Index: 2716216 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.8013. Min Act: -0.1700

Data Index: 405973 (Open Web Text)

Max Activating Token Index: 195

Text #4

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.7116. Min Act: -0.1700

Data Index: 1676302 (Open Web Text)

Max Activating Token Index: 988

Text #5

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.6728. Min Act: -0.1700

Data Index: 8475000 (Open Web Text)

Max Activating Token Index: 281

Text #6

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5968. Min Act: -0.1700

Data Index: 5360466 (Open Web Text)

Max Activating Token Index: 415

Text #7

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5939. Min Act: -0.1700

Data Index: 5359387 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5474. Min Act: -0.1700

Data Index: 3349681 (Open Web Text)

Max Activating Token Index: 311

Text #9

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5475. Min Act: -0.1700

Data Index: 6543788 (Open Web Text)

Max Activating Token Index: 625

Text #10

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5129. Min Act: -0.1700

Data Index: 2441965 (Open Web Text)

Max Activating Token Index: 607

Text #11

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.4801. Min Act: -0.1700

Data Index: 5532120 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5013. Min Act: -0.1700

Data Index: 4015270 (Open Web Text)

Max Activating Token Index: 674

Text #13

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.4786. Min Act: -0.1700

Data Index: 3444192 (Open Web Text)

Max Activating Token Index: 631

Text #14

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5250. Min Act: -0.1700

Data Index: 280123 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.4925. Min Act: -0.1700

Data Index: 539766 (Open Web Text)

Max Activating Token Index: 918

Text #16

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5140. Min Act: -0.1700

Data Index: 1337978 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.5184. Min Act: -0.1700

Data Index: 723853 (Open Web Text)

Max Activating Token Index: 373

Text #18

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.4665. Min Act: -0.1700

Data Index: 5274174 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 4.8824. Min Range: -4.8824

Max Act: 4.4906. Min Act: -0.1700

Data Index: 3656813 (Open Web Text)

Max Activating Token Index: 50