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

Dataset: Open Web Text

Neuron 2571 in Layer 3

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: 6.6574. Min Range: -6.6574

Max Act: 6.6451. Min Act: -0.1700

Data Index: 4406812 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.6574. Min Act: -0.1700

Data Index: 6640072 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.5937. Min Act: -0.1700

Data Index: 7600952 (Open Web Text)

Max Activating Token Index: 207

Text #3

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.5693. Min Act: -0.1700

Data Index: 4836461 (Open Web Text)

Max Activating Token Index: 641

Text #4

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.5052. Min Act: -0.1700

Data Index: 2768669 (Open Web Text)

Max Activating Token Index: 710

Text #5

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.5624. Min Act: -0.1700

Data Index: 2768670 (Open Web Text)

Max Activating Token Index: 192

Text #6

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.5354. Min Act: -0.1700

Data Index: 8546439 (Open Web Text)

Max Activating Token Index: 333

Text #7

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.4628. Min Act: -0.1700

Data Index: 7498878 (Open Web Text)

Max Activating Token Index: 838

Text #8

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.4704. Min Act: -0.1700

Data Index: 986846 (Open Web Text)

Max Activating Token Index: 619

Text #9

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.4783. Min Act: -0.1700

Data Index: 5965044 (Open Web Text)

Max Activating Token Index: 944

Text #10

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.4258. Min Act: -0.1700

Data Index: 2172486 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.3996. Min Act: -0.1700

Data Index: 556867 (Open Web Text)

Max Activating Token Index: 170

Text #12

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.4035. Min Act: -0.1700

Data Index: 3374266 (Open Web Text)

Max Activating Token Index: 726

Text #13

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.4178. Min Act: -0.1700

Data Index: 1956018 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.4658. Min Act: -0.1700

Data Index: 3498652 (Open Web Text)

Max Activating Token Index: 485

Text #15

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.4216. Min Act: -0.1700

Data Index: 7377225 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.3454. Min Act: -0.1700

Data Index: 4961820 (Open Web Text)

Max Activating Token Index: 449

Text #17

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.3712. Min Act: -0.1700

Data Index: 2294107 (Open Web Text)

Max Activating Token Index: 704

Text #18

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.3718. Min Act: -0.1700

Data Index: 6449427 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 6.6574. Min Range: -6.6574

Max Act: 6.2899. Min Act: -0.1700

Data Index: 5971370 (Open Web Text)

Max Activating Token Index: 175