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

Dataset: Open Web Text

Neuron 1267 in Layer 1

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: 1.7688. Min Range: -1.7688

Max Act: 1.7688. Min Act: -0.1700

Data Index: 4507211 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6511. Min Act: -0.1689

Data Index: 371822 (Open Web Text)

Max Activating Token Index: 720

Text #2

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6437. Min Act: -0.1700

Data Index: 4935518 (Open Web Text)

Max Activating Token Index: 880

Text #3

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6459. Min Act: -0.1700

Data Index: 3210116 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6308. Min Act: -0.1700

Data Index: 4589424 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6404. Min Act: -0.1699

Data Index: 4194160 (Open Web Text)

Max Activating Token Index: 669

Text #6

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6275. Min Act: -0.1700

Data Index: 4081896 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6323. Min Act: -0.1700

Data Index: 4329960 (Open Web Text)

Max Activating Token Index: 671

Text #8

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6269. Min Act: -0.1700

Data Index: 6792641 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6120. Min Act: -0.1700

Data Index: 3749539 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6154. Min Act: -0.1700

Data Index: 4641123 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5999. Min Act: -0.1700

Data Index: 1553023 (Open Web Text)

Max Activating Token Index: 391

Text #12

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.6021. Min Act: -0.1700

Data Index: 2654800 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5995. Min Act: -0.1700

Data Index: 7732509 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5930. Min Act: -0.1700

Data Index: 1072795 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5926. Min Act: -0.1700

Data Index: 6905251 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5963. Min Act: -0.1700

Data Index: 371823 (Open Web Text)

Max Activating Token Index: 935

Text #17

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5889. Min Act: -0.1699

Data Index: 823313 (Open Web Text)

Max Activating Token Index: 295

Text #18

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5899. Min Act: -0.1697

Data Index: 5829868 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5899. Min Act: -0.1698

Data Index: 3204722 (Open Web Text)

Max Activating Token Index: 28