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

Dataset: Open Web Text

Neuron 321 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: 4.7648. Min Range: -4.7648

Max Act: 4.7492. Min Act: -0.1700

Data Index: 6827837 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.7648. Min Act: -0.1700

Data Index: 7492110 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.7186. Min Act: -0.1700

Data Index: 3698013 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6701. Min Act: -0.1700

Data Index: 1550860 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6918. Min Act: -0.1700

Data Index: 3013297 (Open Web Text)

Max Activating Token Index: 689

Text #5

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6477. Min Act: -0.1700

Data Index: 1627740 (Open Web Text)

Max Activating Token Index: 388

Text #6

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6460. Min Act: -0.1700

Data Index: 2554570 (Open Web Text)

Max Activating Token Index: 286

Text #7

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6155. Min Act: -0.1700

Data Index: 3840866 (Open Web Text)

Max Activating Token Index: 132

Text #8

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6001. Min Act: -0.1700

Data Index: 4550863 (Open Web Text)

Max Activating Token Index: 535

Text #9

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6330. Min Act: -0.1700

Data Index: 7916191 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6183. Min Act: -0.1700

Data Index: 4810395 (Open Web Text)

Max Activating Token Index: 439

Text #11

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5794. Min Act: -0.1700

Data Index: 2786231 (Open Web Text)

Max Activating Token Index: 175

Text #12

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5624. Min Act: -0.1700

Data Index: 7592021 (Open Web Text)

Max Activating Token Index: 969

Text #13

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5937. Min Act: -0.1700

Data Index: 6536800 (Open Web Text)

Max Activating Token Index: 526

Text #14

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5565. Min Act: -0.1700

Data Index: 5208441 (Open Web Text)

Max Activating Token Index: 894

Text #15

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5433. Min Act: -0.1700

Data Index: 6228026 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5262. Min Act: -0.1700

Data Index: 5205464 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5201. Min Act: -0.1700

Data Index: 3086494 (Open Web Text)

Max Activating Token Index: 373

Text #18

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.4962. Min Act: -0.1700

Data Index: 7394269 (Open Web Text)

Max Activating Token Index: 65

Text #19

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5432. Min Act: -0.1700

Data Index: 4722391 (Open Web Text)

Max Activating Token Index: 968