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

Dataset: Open Web Text

Neuron 466 in Layer 5

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: 4.9412. Min Range: -4.9412

Max Act: 4.9412. Min Act: -0.1700

Data Index: 2948045 (Open Web Text)

Max Activating Token Index: 321

Text #1

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.6821. Min Act: -0.1700

Data Index: 625117 (Open Web Text)

Max Activating Token Index: 1003

Text #2

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.6701. Min Act: -0.1700

Data Index: 3598397 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.6572. Min Act: -0.1700

Data Index: 7672589 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.6934. Min Act: -0.1700

Data Index: 7088531 (Open Web Text)

Max Activating Token Index: 254

Text #5

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5998. Min Act: -0.1700

Data Index: 2324456 (Open Web Text)

Max Activating Token Index: 597

Text #6

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.6305. Min Act: -0.1700

Data Index: 5066013 (Open Web Text)

Max Activating Token Index: 337

Text #7

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.6277. Min Act: -0.1700

Data Index: 5225501 (Open Web Text)

Max Activating Token Index: 804

Text #8

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.6171. Min Act: -0.1700

Data Index: 2012330 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5772. Min Act: -0.1700

Data Index: 3441562 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5787. Min Act: -0.1700

Data Index: 6528889 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5606. Min Act: -0.1700

Data Index: 5224663 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.6089. Min Act: -0.1700

Data Index: 7887430 (Open Web Text)

Max Activating Token Index: 453

Text #13

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5917. Min Act: -0.1700

Data Index: 5387877 (Open Web Text)

Max Activating Token Index: 792

Text #14

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5702. Min Act: -0.1700

Data Index: 3623568 (Open Web Text)

Max Activating Token Index: 259

Text #15

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5609. Min Act: -0.1700

Data Index: 7500998 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5128. Min Act: -0.1700

Data Index: 8118929 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5813. Min Act: -0.1700

Data Index: 5445459 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5865. Min Act: -0.1700

Data Index: 8142668 (Open Web Text)

Max Activating Token Index: 210

Text #19

Max Range: 4.9412. Min Range: -4.9412

Max Act: 4.5673. Min Act: -0.1700

Data Index: 8698123 (Open Web Text)

Max Activating Token Index: 560