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

Dataset: Open Web Text

Neuron 1298 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: 5.3233. Min Range: -5.3233

Max Act: 5.3233. Min Act: -0.1700

Data Index: 6112303 (Open Web Text)

Max Activating Token Index: 717

Text #1

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.2995. Min Act: -0.1700

Data Index: 4931350 (Open Web Text)

Max Activating Token Index: 922

Text #2

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.2101. Min Act: -0.1700

Data Index: 7506017 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1609. Min Act: -0.1700

Data Index: 4683061 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1732. Min Act: -0.1700

Data Index: 22032 (Open Web Text)

Max Activating Token Index: 982

Text #5

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1098. Min Act: -0.1700

Data Index: 7310735 (Open Web Text)

Max Activating Token Index: 224

Text #6

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0758. Min Act: -0.1700

Data Index: 4350290 (Open Web Text)

Max Activating Token Index: 827

Text #7

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0400. Min Act: -0.1700

Data Index: 628899 (Open Web Text)

Max Activating Token Index: 632

Text #8

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0420. Min Act: -0.1700

Data Index: 3595551 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0259. Min Act: -0.1700

Data Index: 5914093 (Open Web Text)

Max Activating Token Index: 228

Text #10

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0180. Min Act: -0.1700

Data Index: 4396567 (Open Web Text)

Max Activating Token Index: 591

Text #11

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.9759. Min Act: -0.1700

Data Index: 4417572 (Open Web Text)

Max Activating Token Index: 653

Text #12

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.9304. Min Act: -0.1700

Data Index: 6325881 (Open Web Text)

Max Activating Token Index: 840

Text #13

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.9587. Min Act: -0.1700

Data Index: 4536794 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.9216. Min Act: -0.1700

Data Index: 4536793 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.9234. Min Act: -0.1700

Data Index: 2640373 (Open Web Text)

Max Activating Token Index: 575

Text #16

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.9093. Min Act: -0.1700

Data Index: 5177629 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.9478. Min Act: -0.1700

Data Index: 6893245 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.8764. Min Act: -0.1700

Data Index: 831163 (Open Web Text)

Max Activating Token Index: 950

Text #19

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.8167. Min Act: -0.1700

Data Index: 6581472 (Open Web Text)

Max Activating Token Index: 842