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

Dataset: Open Web Text

Neuron 2397 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: 4.7704. Min Range: -4.7704

Max Act: 4.7704. Min Act: -0.1700

Data Index: 593415 (Open Web Text)

Max Activating Token Index: 322

Text #1

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.6895. Min Act: -0.1700

Data Index: 2138548 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.6775. Min Act: -0.1700

Data Index: 7935214 (Open Web Text)

Max Activating Token Index: 301

Text #3

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.6989. Min Act: -0.1700

Data Index: 6567930 (Open Web Text)

Max Activating Token Index: 645

Text #4

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.6761. Min Act: -0.1700

Data Index: 3938272 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.6465. Min Act: -0.1700

Data Index: 1967642 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.6472. Min Act: -0.1700

Data Index: 3373233 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.6293. Min Act: -0.1700

Data Index: 853814 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5971. Min Act: -0.1700

Data Index: 7672505 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5878. Min Act: -0.1700

Data Index: 1610828 (Open Web Text)

Max Activating Token Index: 279

Text #10

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5872. Min Act: -0.1700

Data Index: 4090627 (Open Web Text)

Max Activating Token Index: 897

Text #11

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5749. Min Act: -0.1700

Data Index: 1620825 (Open Web Text)

Max Activating Token Index: 969

Text #12

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.6025. Min Act: -0.1700

Data Index: 123442 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5929. Min Act: -0.1700

Data Index: 6009780 (Open Web Text)

Max Activating Token Index: 719

Text #14

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5829. Min Act: -0.1700

Data Index: 1041460 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5594. Min Act: -0.1700

Data Index: 5242612 (Open Web Text)

Max Activating Token Index: 411

Text #16

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5161. Min Act: -0.1700

Data Index: 1534809 (Open Web Text)

Max Activating Token Index: 223

Text #17

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5555. Min Act: -0.1700

Data Index: 1916020 (Open Web Text)

Max Activating Token Index: 176

Text #18

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5615. Min Act: -0.1700

Data Index: 1155301 (Open Web Text)

Max Activating Token Index: 982

Text #19

Max Range: 4.7704. Min Range: -4.7704

Max Act: 4.5450. Min Act: -0.1700

Data Index: 3221843 (Open Web Text)

Max Activating Token Index: 1010