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

Dataset: Open Web Text

Neuron 504 in Layer 6

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: 3.9264. Min Range: -3.9264

Max Act: 3.9264. Min Act: -0.1700

Data Index: 2798287 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.9262. Min Act: -0.1700

Data Index: 7502775 (Open Web Text)

Max Activating Token Index: 1002

Text #2

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.9103. Min Act: -0.1700

Data Index: 5879854 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8906. Min Act: -0.1700

Data Index: 2979683 (Open Web Text)

Max Activating Token Index: 984

Text #4

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8955. Min Act: -0.1700

Data Index: 5385958 (Open Web Text)

Max Activating Token Index: 1008

Text #5

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.9141. Min Act: -0.1700

Data Index: 2858280 (Open Web Text)

Max Activating Token Index: 1018

Text #6

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8858. Min Act: -0.1700

Data Index: 2917486 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8772. Min Act: -0.1700

Data Index: 1825342 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8673. Min Act: -0.1700

Data Index: 1277307 (Open Web Text)

Max Activating Token Index: 937

Text #9

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8892. Min Act: -0.1700

Data Index: 1277311 (Open Web Text)

Max Activating Token Index: 960

Text #10

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8878. Min Act: -0.1700

Data Index: 8761068 (Open Web Text)

Max Activating Token Index: 571

Text #11

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8768. Min Act: -0.1700

Data Index: 8700666 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8904. Min Act: -0.1700

Data Index: 4864656 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8740. Min Act: -0.1700

Data Index: 6870872 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8643. Min Act: -0.1700

Data Index: 7602630 (Open Web Text)

Max Activating Token Index: 407

Text #15

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8489. Min Act: -0.1700

Data Index: 5005507 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8482. Min Act: -0.1700

Data Index: 7364116 (Open Web Text)

Max Activating Token Index: 543

Text #17

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8259. Min Act: -0.1700

Data Index: 2681091 (Open Web Text)

Max Activating Token Index: 81

Text #18

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8395. Min Act: -0.1700

Data Index: 804880 (Open Web Text)

Max Activating Token Index: 969

Text #19

Max Range: 3.9264. Min Range: -3.9264

Max Act: 3.8629. Min Act: -0.1700

Data Index: 301654 (Open Web Text)

Max Activating Token Index: 617