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

Dataset: Open Web Text

Neuron 912 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: 3.9638. Min Range: -3.9638

Max Act: 3.9638. Min Act: -0.1700

Data Index: 8573824 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.8355. Min Act: -0.1700

Data Index: 5025914 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.7595. Min Act: -0.1700

Data Index: 6497062 (Open Web Text)

Max Activating Token Index: 429

Text #3

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.7284. Min Act: -0.1700

Data Index: 5422735 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6762. Min Act: -0.1700

Data Index: 5557242 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6737. Min Act: -0.1700

Data Index: 2188971 (Open Web Text)

Max Activating Token Index: 316

Text #6

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6748. Min Act: -0.1700

Data Index: 4381154 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6501. Min Act: -0.1700

Data Index: 4102968 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6588. Min Act: -0.1700

Data Index: 6612564 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6522. Min Act: -0.1700

Data Index: 1578111 (Open Web Text)

Max Activating Token Index: 757

Text #10

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6002. Min Act: -0.1700

Data Index: 2284231 (Open Web Text)

Max Activating Token Index: 477

Text #11

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6182. Min Act: -0.1700

Data Index: 6351822 (Open Web Text)

Max Activating Token Index: 68

Text #12

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.5935. Min Act: -0.1700

Data Index: 627474 (Open Web Text)

Max Activating Token Index: 939

Text #13

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.5898. Min Act: -0.1700

Data Index: 5626867 (Open Web Text)

Max Activating Token Index: 135

Text #14

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.6054. Min Act: -0.1700

Data Index: 8689238 (Open Web Text)

Max Activating Token Index: 234

Text #15

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.5885. Min Act: -0.1700

Data Index: 7312639 (Open Web Text)

Max Activating Token Index: 359

Text #16

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.5922. Min Act: -0.1700

Data Index: 1983060 (Open Web Text)

Max Activating Token Index: 672

Text #17

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.5795. Min Act: -0.1700

Data Index: 3641643 (Open Web Text)

Max Activating Token Index: 119

Text #18

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.5878. Min Act: -0.1700

Data Index: 4381151 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.5584. Min Act: -0.1700

Data Index: 4463820 (Open Web Text)

Max Activating Token Index: 124