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

Dataset: Open Web Text

Neuron 86 in Layer 2

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: 2.9023. Min Range: -2.9023

Max Act: 2.9023. Min Act: -0.1700

Data Index: 190136 (Open Web Text)

Max Activating Token Index: 100

Text #1

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.8608. Min Act: -0.1700

Data Index: 8166899 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.7513. Min Act: -0.1700

Data Index: 8414844 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.7607. Min Act: -0.1700

Data Index: 8582078 (Open Web Text)

Max Activating Token Index: 239

Text #4

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.7362. Min Act: -0.1700

Data Index: 7862235 (Open Web Text)

Max Activating Token Index: 429

Text #5

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.7404. Min Act: -0.1700

Data Index: 1881627 (Open Web Text)

Max Activating Token Index: 121

Text #6

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.7200. Min Act: -0.1700

Data Index: 7063279 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.7122. Min Act: -0.1700

Data Index: 1757150 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6987. Min Act: -0.1700

Data Index: 494233 (Open Web Text)

Max Activating Token Index: 271

Text #9

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6948. Min Act: -0.1700

Data Index: 1374864 (Open Web Text)

Max Activating Token Index: 201

Text #10

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.7044. Min Act: -0.1700

Data Index: 3625913 (Open Web Text)

Max Activating Token Index: 540

Text #11

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6770. Min Act: -0.1700

Data Index: 1509410 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6903. Min Act: -0.1700

Data Index: 8582077 (Open Web Text)

Max Activating Token Index: 646

Text #13

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6696. Min Act: -0.1700

Data Index: 1022097 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6594. Min Act: -0.1700

Data Index: 6973570 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6593. Min Act: -0.1700

Data Index: 6234216 (Open Web Text)

Max Activating Token Index: 296

Text #16

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6535. Min Act: -0.1700

Data Index: 2527375 (Open Web Text)

Max Activating Token Index: 44

Text #17

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6487. Min Act: -0.1700

Data Index: 726446 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6323. Min Act: -0.1700

Data Index: 4433223 (Open Web Text)

Max Activating Token Index: 784

Text #19

Max Range: 2.9023. Min Range: -2.9023

Max Act: 2.6473. Min Act: -0.1700

Data Index: 4812914 (Open Web Text)

Max Activating Token Index: 121