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

Dataset: Open Web Text

Neuron 3000 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: 5.0604. Min Range: -5.0604

Max Act: 5.0604. Min Act: -0.1700

Data Index: 5316055 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 5.0604. Min Range: -5.0604

Max Act: 5.0293. Min Act: -0.1700

Data Index: 5065779 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 5.0604. Min Range: -5.0604

Max Act: 5.0272. Min Act: -0.1700

Data Index: 6906100 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 5.0604. Min Range: -5.0604

Max Act: 5.0152. Min Act: -0.1700

Data Index: 2815484 (Open Web Text)

Max Activating Token Index: 240

Text #4

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.9779. Min Act: -0.1700

Data Index: 1224307 (Open Web Text)

Max Activating Token Index: 937

Text #5

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.9738. Min Act: -0.1700

Data Index: 8367211 (Open Web Text)

Max Activating Token Index: 164

Text #6

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.9664. Min Act: -0.1700

Data Index: 4371636 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.9795. Min Act: -0.1700

Data Index: 1636524 (Open Web Text)

Max Activating Token Index: 662

Text #8

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.9557. Min Act: -0.1700

Data Index: 3193683 (Open Web Text)

Max Activating Token Index: 880

Text #9

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.9311. Min Act: -0.1700

Data Index: 5841842 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.9024. Min Act: -0.1700

Data Index: 2262270 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.8852. Min Act: -0.1700

Data Index: 6628485 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.8927. Min Act: -0.1700

Data Index: 4283744 (Open Web Text)

Max Activating Token Index: 83

Text #13

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.8629. Min Act: -0.1700

Data Index: 8248282 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.8693. Min Act: -0.1700

Data Index: 8314180 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.8594. Min Act: -0.1700

Data Index: 7917880 (Open Web Text)

Max Activating Token Index: 64

Text #16

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.8991. Min Act: -0.1700

Data Index: 5868346 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.9033. Min Act: -0.1700

Data Index: 8805876 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.8895. Min Act: -0.1700

Data Index: 8813237 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 5.0604. Min Range: -5.0604

Max Act: 4.8941. Min Act: -0.1700

Data Index: 1618428 (Open Web Text)

Max Activating Token Index: 791