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

Dataset: Open Web Text

Neuron 1769 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: 3.7876. Min Range: -3.7876

Max Act: 3.7876. Min Act: -0.1700

Data Index: 6449051 (Open Web Text)

Max Activating Token Index: 79

Text #1

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7572. Min Act: -0.1700

Data Index: 8493835 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7262. Min Act: -0.1700

Data Index: 3839212 (Open Web Text)

Max Activating Token Index: 291

Text #3

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7388. Min Act: -0.1700

Data Index: 778894 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7362. Min Act: -0.1700

Data Index: 2014684 (Open Web Text)

Max Activating Token Index: 981

Text #5

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7151. Min Act: -0.1700

Data Index: 4264267 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7259. Min Act: -0.1700

Data Index: 2977081 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7570. Min Act: -0.1700

Data Index: 6967254 (Open Web Text)

Max Activating Token Index: 823

Text #8

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7511. Min Act: -0.1700

Data Index: 4306055 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6905. Min Act: -0.1700

Data Index: 7531723 (Open Web Text)

Max Activating Token Index: 944

Text #10

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6861. Min Act: -0.1700

Data Index: 5353294 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6782. Min Act: -0.1700

Data Index: 5068444 (Open Web Text)

Max Activating Token Index: 164

Text #12

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7098. Min Act: -0.1700

Data Index: 3271408 (Open Web Text)

Max Activating Token Index: 966

Text #13

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6827. Min Act: -0.1700

Data Index: 29810 (Open Web Text)

Max Activating Token Index: 414

Text #14

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6886. Min Act: -0.1700

Data Index: 6864100 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6834. Min Act: -0.1700

Data Index: 4103404 (Open Web Text)

Max Activating Token Index: 1005

Text #16

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6954. Min Act: -0.1700

Data Index: 6857200 (Open Web Text)

Max Activating Token Index: 277

Text #17

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6891. Min Act: -0.1700

Data Index: 5832732 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6661. Min Act: -0.1700

Data Index: 3732662 (Open Web Text)

Max Activating Token Index: 321

Text #19

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6831. Min Act: -0.1700

Data Index: 391644 (Open Web Text)

Max Activating Token Index: 826