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

Dataset: Open Web Text

Neuron 75 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: 4.6772. Min Range: -4.6772

Max Act: 4.6772. Min Act: -0.1700

Data Index: 8020730 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.6546. Min Act: -0.1700

Data Index: 5270106 (Open Web Text)

Max Activating Token Index: 457

Text #2

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5747. Min Act: -0.1700

Data Index: 908171 (Open Web Text)

Max Activating Token Index: 320

Text #3

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5403. Min Act: -0.1700

Data Index: 3599345 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5350. Min Act: -0.1700

Data Index: 5598258 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5510. Min Act: -0.1700

Data Index: 3706251 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5253. Min Act: -0.1700

Data Index: 5299917 (Open Web Text)

Max Activating Token Index: 718

Text #7

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5616. Min Act: -0.1700

Data Index: 3336469 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5393. Min Act: -0.1700

Data Index: 8734757 (Open Web Text)

Max Activating Token Index: 106

Text #9

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5071. Min Act: -0.1700

Data Index: 8239809 (Open Web Text)

Max Activating Token Index: 354

Text #10

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.4917. Min Act: -0.1700

Data Index: 1147111 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.4713. Min Act: -0.1700

Data Index: 1886605 (Open Web Text)

Max Activating Token Index: 480

Text #12

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5027. Min Act: -0.1700

Data Index: 5450149 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.4842. Min Act: -0.1700

Data Index: 5251920 (Open Web Text)

Max Activating Token Index: 631

Text #14

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.5009. Min Act: -0.1700

Data Index: 2975276 (Open Web Text)

Max Activating Token Index: 412

Text #15

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.4975. Min Act: -0.1700

Data Index: 5709719 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.4900. Min Act: -0.1700

Data Index: 1408434 (Open Web Text)

Max Activating Token Index: 50

Text #17

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.4746. Min Act: -0.1700

Data Index: 6289995 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.4911. Min Act: -0.1700

Data Index: 1965116 (Open Web Text)

Max Activating Token Index: 715

Text #19

Max Range: 4.6772. Min Range: -4.6772

Max Act: 4.4795. Min Act: -0.1700

Data Index: 6172627 (Open Web Text)

Max Activating Token Index: 733