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

Dataset: Open Web Text

Neuron 1774 in Layer 1

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: 4.6047. Min Range: -4.6047

Max Act: 4.6047. Min Act: -0.1700

Data Index: 6614642 (Open Web Text)

Max Activating Token Index: 828

Text #1

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.5492. Min Act: -0.1700

Data Index: 5075364 (Open Web Text)

Max Activating Token Index: 167

Text #2

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.5609. Min Act: -0.1700

Data Index: 5148308 (Open Web Text)

Max Activating Token Index: 460

Text #3

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.5317. Min Act: -0.1700

Data Index: 5052199 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4822. Min Act: -0.1700

Data Index: 7889703 (Open Web Text)

Max Activating Token Index: 162

Text #5

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.5068. Min Act: -0.1700

Data Index: 491072 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4815. Min Act: -0.1700

Data Index: 8341371 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4831. Min Act: -0.1700

Data Index: 15095 (Open Web Text)

Max Activating Token Index: 416

Text #8

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4921. Min Act: -0.1700

Data Index: 7577561 (Open Web Text)

Max Activating Token Index: 783

Text #9

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4836. Min Act: -0.1700

Data Index: 4327731 (Open Web Text)

Max Activating Token Index: 767

Text #10

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4697. Min Act: -0.1700

Data Index: 4240555 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4844. Min Act: -0.1700

Data Index: 7172410 (Open Web Text)

Max Activating Token Index: 1021

Text #12

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4714. Min Act: -0.1700

Data Index: 652197 (Open Web Text)

Max Activating Token Index: 270

Text #13

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4615. Min Act: -0.1700

Data Index: 7828550 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4697. Min Act: -0.1700

Data Index: 2975339 (Open Web Text)

Max Activating Token Index: 717

Text #15

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4637. Min Act: -0.1700

Data Index: 1349265 (Open Web Text)

Max Activating Token Index: 458

Text #16

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4879. Min Act: -0.1700

Data Index: 1684425 (Open Web Text)

Max Activating Token Index: 868

Text #17

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4519. Min Act: -0.1700

Data Index: 8611331 (Open Web Text)

Max Activating Token Index: 208

Text #18

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4539. Min Act: -0.1700

Data Index: 4001118 (Open Web Text)

Max Activating Token Index: 245

Text #19

Max Range: 4.6047. Min Range: -4.6047

Max Act: 4.4153. Min Act: -0.1700

Data Index: 791028 (Open Web Text)

Max Activating Token Index: 326