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

Dataset: Open Web Text

Neuron 794 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: 4.4826. Min Range: -4.4826

Max Act: 4.4826. Min Act: -0.1700

Data Index: 1495193 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.4320. Min Act: -0.1700

Data Index: 1495207 (Open Web Text)

Max Activating Token Index: 399

Text #2

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.3853. Min Act: -0.1700

Data Index: 373451 (Open Web Text)

Max Activating Token Index: 499

Text #3

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.3430. Min Act: -0.1700

Data Index: 1597378 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.3439. Min Act: -0.1700

Data Index: 8765337 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.3117. Min Act: -0.1700

Data Index: 4599573 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2641. Min Act: -0.1700

Data Index: 1597392 (Open Web Text)

Max Activating Token Index: 708

Text #7

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2792. Min Act: -0.1700

Data Index: 4599562 (Open Web Text)

Max Activating Token Index: 315

Text #8

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2944. Min Act: -0.1700

Data Index: 373464 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2106. Min Act: -0.1700

Data Index: 6249094 (Open Web Text)

Max Activating Token Index: 516

Text #10

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2550. Min Act: -0.1700

Data Index: 7783051 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2576. Min Act: -0.1700

Data Index: 2296691 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2294. Min Act: -0.1700

Data Index: 3010681 (Open Web Text)

Max Activating Token Index: 331

Text #13

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2013. Min Act: -0.1700

Data Index: 7783041 (Open Web Text)

Max Activating Token Index: 875

Text #14

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2226. Min Act: -0.1700

Data Index: 2289727 (Open Web Text)

Max Activating Token Index: 486

Text #15

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.1797. Min Act: -0.1700

Data Index: 3604960 (Open Web Text)

Max Activating Token Index: 30

Text #16

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2029. Min Act: -0.1700

Data Index: 7191513 (Open Web Text)

Max Activating Token Index: 859

Text #17

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2111. Min Act: -0.1700

Data Index: 3010700 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.2028. Min Act: -0.1700

Data Index: 6249108 (Open Web Text)

Max Activating Token Index: 662

Text #19

Max Range: 4.4826. Min Range: -4.4826

Max Act: 4.1915. Min Act: -0.1700

Data Index: 2215173 (Open Web Text)

Max Activating Token Index: 805