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

Dataset: Open Web Text

Neuron 2264 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: 3.2210. Min Range: -3.2210

Max Act: 3.2210. Min Act: -0.1700

Data Index: 1677130 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.1733. Min Act: -0.1700

Data Index: 5203697 (Open Web Text)

Max Activating Token Index: 682

Text #2

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.0918. Min Act: -0.1700

Data Index: 7412243 (Open Web Text)

Max Activating Token Index: 165

Text #3

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.0891. Min Act: -0.1700

Data Index: 3022475 (Open Web Text)

Max Activating Token Index: 799

Text #4

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.0420. Min Act: -0.1700

Data Index: 571066 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.0460. Min Act: -0.1700

Data Index: 1829988 (Open Web Text)

Max Activating Token Index: 443

Text #6

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.0280. Min Act: -0.1700

Data Index: 5136651 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.0042. Min Act: -0.1700

Data Index: 3599575 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9887. Min Act: -0.1700

Data Index: 8814190 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.0241. Min Act: -0.1700

Data Index: 217337 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 3.2210. Min Range: -3.2210

Max Act: 3.0002. Min Act: -0.1700

Data Index: 8608571 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9889. Min Act: -0.1700

Data Index: 5654027 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9770. Min Act: -0.1700

Data Index: 6989830 (Open Web Text)

Max Activating Token Index: 880

Text #13

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9862. Min Act: -0.1700

Data Index: 1474356 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9539. Min Act: -0.1700

Data Index: 6503847 (Open Web Text)

Max Activating Token Index: 623

Text #15

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9416. Min Act: -0.1700

Data Index: 7184628 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9221. Min Act: -0.1700

Data Index: 903118 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9616. Min Act: -0.1700

Data Index: 3763536 (Open Web Text)

Max Activating Token Index: 744

Text #18

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9678. Min Act: -0.1700

Data Index: 8410389 (Open Web Text)

Max Activating Token Index: 768

Text #19

Max Range: 3.2210. Min Range: -3.2210

Max Act: 2.9561. Min Act: -0.1700

Data Index: 4002996 (Open Web Text)

Max Activating Token Index: 339