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

Dataset: Open Web Text

Neuron 1878 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: 2.1263. Min Range: -2.1263

Max Act: 2.1263. Min Act: -0.1700

Data Index: 6039459 (Open Web Text)

Max Activating Token Index: 478

Text #1

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.1031. Min Act: -0.1700

Data Index: 3529164 (Open Web Text)

Max Activating Token Index: 379

Text #2

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.1035. Min Act: -0.1700

Data Index: 6521124 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.1037. Min Act: -0.1700

Data Index: 193911 (Open Web Text)

Max Activating Token Index: 455

Text #4

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0915. Min Act: -0.1700

Data Index: 5179034 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0840. Min Act: -0.1700

Data Index: 3596521 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0882. Min Act: -0.1700

Data Index: 2322396 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0898. Min Act: -0.1700

Data Index: 4756258 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0802. Min Act: -0.1700

Data Index: 7920826 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0788. Min Act: -0.1700

Data Index: 302717 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0789. Min Act: -0.1700

Data Index: 5405613 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0731. Min Act: -0.1700

Data Index: 1635824 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0841. Min Act: -0.1700

Data Index: 8648058 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0695. Min Act: -0.1700

Data Index: 3254905 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0718. Min Act: -0.1700

Data Index: 5279795 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0748. Min Act: -0.1700

Data Index: 5408557 (Open Web Text)

Max Activating Token Index: 537

Text #16

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0744. Min Act: -0.1700

Data Index: 2336194 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0714. Min Act: -0.1700

Data Index: 2056319 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0699. Min Act: -0.1700

Data Index: 1706264 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 2.1263. Min Range: -2.1263

Max Act: 2.0695. Min Act: -0.1700

Data Index: 1995714 (Open Web Text)

Max Activating Token Index: 5