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

Dataset: Open Web Text

Neuron 1638 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: 4.0971. Min Range: -4.0971

Max Act: 4.0971. Min Act: -0.1700

Data Index: 6407322 (Open Web Text)

Max Activating Token Index: 126

Text #1

Max Range: 4.0971. Min Range: -4.0971

Max Act: 4.0600. Min Act: -0.1700

Data Index: 4800149 (Open Web Text)

Max Activating Token Index: 578

Text #2

Max Range: 4.0971. Min Range: -4.0971

Max Act: 4.0451. Min Act: -0.1700

Data Index: 3437999 (Open Web Text)

Max Activating Token Index: 764

Text #3

Max Range: 4.0971. Min Range: -4.0971

Max Act: 4.0028. Min Act: -0.1700

Data Index: 4217250 (Open Web Text)

Max Activating Token Index: 813

Text #4

Max Range: 4.0971. Min Range: -4.0971

Max Act: 4.0429. Min Act: -0.1700

Data Index: 7698112 (Open Web Text)

Max Activating Token Index: 814

Text #5

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9811. Min Act: -0.1700

Data Index: 8361253 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9767. Min Act: -0.1700

Data Index: 3932636 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9927. Min Act: -0.1700

Data Index: 5484403 (Open Web Text)

Max Activating Token Index: 916

Text #8

Max Range: 4.0971. Min Range: -4.0971

Max Act: 4.0006. Min Act: -0.1700

Data Index: 7961402 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9690. Min Act: -0.1700

Data Index: 4631273 (Open Web Text)

Max Activating Token Index: 288

Text #10

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9726. Min Act: -0.1700

Data Index: 8054561 (Open Web Text)

Max Activating Token Index: 681

Text #11

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9758. Min Act: -0.1700

Data Index: 6588737 (Open Web Text)

Max Activating Token Index: 467

Text #12

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9857. Min Act: -0.1700

Data Index: 161034 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9598. Min Act: -0.1700

Data Index: 8374973 (Open Web Text)

Max Activating Token Index: 200

Text #14

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9328. Min Act: -0.1700

Data Index: 3714535 (Open Web Text)

Max Activating Token Index: 447

Text #15

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9226. Min Act: -0.1700

Data Index: 2583281 (Open Web Text)

Max Activating Token Index: 846

Text #16

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9292. Min Act: -0.1700

Data Index: 1261573 (Open Web Text)

Max Activating Token Index: 836

Text #17

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9492. Min Act: -0.1700

Data Index: 6365931 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9260. Min Act: -0.1700

Data Index: 5649444 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 4.0971. Min Range: -4.0971

Max Act: 3.9351. Min Act: -0.1700

Data Index: 4858401 (Open Web Text)

Max Activating Token Index: 539