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

Dataset: Open Web Text

Neuron 1893 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: 4.4093. Min Range: -4.4093

Max Act: 4.4093. Min Act: -0.1700

Data Index: 899168 (Open Web Text)

Max Activating Token Index: 534

Text #1

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.1807. Min Act: -0.1700

Data Index: 6641170 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.1434. Min Act: -0.1700

Data Index: 8432771 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0957. Min Act: -0.1700

Data Index: 193922 (Open Web Text)

Max Activating Token Index: 446

Text #4

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.1018. Min Act: -0.1700

Data Index: 6988824 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0683. Min Act: -0.1700

Data Index: 2079422 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0777. Min Act: -0.1700

Data Index: 653856 (Open Web Text)

Max Activating Token Index: 320

Text #7

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0518. Min Act: -0.1700

Data Index: 1415876 (Open Web Text)

Max Activating Token Index: 336

Text #8

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0570. Min Act: -0.1700

Data Index: 3789786 (Open Web Text)

Max Activating Token Index: 372

Text #9

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0684. Min Act: -0.1700

Data Index: 3777154 (Open Web Text)

Max Activating Token Index: 701

Text #10

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0426. Min Act: -0.1700

Data Index: 5318516 (Open Web Text)

Max Activating Token Index: 343

Text #11

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0211. Min Act: -0.1700

Data Index: 5628478 (Open Web Text)

Max Activating Token Index: 919

Text #12

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0451. Min Act: -0.1700

Data Index: 5918222 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0206. Min Act: -0.1700

Data Index: 7410027 (Open Web Text)

Max Activating Token Index: 303

Text #14

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0065. Min Act: -0.1700

Data Index: 5653289 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 4.4093. Min Range: -4.4093

Max Act: 4.0025. Min Act: -0.1700

Data Index: 692470 (Open Web Text)

Max Activating Token Index: 90

Text #16

Max Range: 4.4093. Min Range: -4.4093

Max Act: 3.9727. Min Act: -0.1700

Data Index: 961560 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 4.4093. Min Range: -4.4093

Max Act: 3.9550. Min Act: -0.1700

Data Index: 812930 (Open Web Text)

Max Activating Token Index: 719

Text #18

Max Range: 4.4093. Min Range: -4.4093

Max Act: 3.9572. Min Act: -0.1700

Data Index: 965312 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 4.4093. Min Range: -4.4093

Max Act: 3.9745. Min Act: -0.1700

Data Index: 5576455 (Open Web Text)

Max Activating Token Index: 542