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

Dataset: Open Web Text

Neuron 1508 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: 4.2822. Min Range: -4.2822

Max Act: 4.2822. Min Act: -0.1700

Data Index: 4622611 (Open Web Text)

Max Activating Token Index: 268

Text #1

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.1708. Min Act: -0.1700

Data Index: 8522969 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.1878. Min Act: -0.1700

Data Index: 4523996 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.1952. Min Act: -0.1700

Data Index: 2259140 (Open Web Text)

Max Activating Token Index: 773

Text #4

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.1289. Min Act: -0.1700

Data Index: 7043707 (Open Web Text)

Max Activating Token Index: 616

Text #5

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.1622. Min Act: -0.1700

Data Index: 1485833 (Open Web Text)

Max Activating Token Index: 839

Text #6

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.1398. Min Act: -0.1700

Data Index: 1149136 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0821. Min Act: -0.1700

Data Index: 7326194 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.1235. Min Act: -0.1700

Data Index: 2747503 (Open Web Text)

Max Activating Token Index: 433

Text #9

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0438. Min Act: -0.1700

Data Index: 5417720 (Open Web Text)

Max Activating Token Index: 175

Text #10

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0696. Min Act: -0.1700

Data Index: 5129549 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.1072. Min Act: -0.1700

Data Index: 5982449 (Open Web Text)

Max Activating Token Index: 288

Text #12

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0456. Min Act: -0.1700

Data Index: 5989350 (Open Web Text)

Max Activating Token Index: 336

Text #13

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0529. Min Act: -0.1700

Data Index: 5173041 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0606. Min Act: -0.1700

Data Index: 7323754 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0517. Min Act: -0.1700

Data Index: 2650389 (Open Web Text)

Max Activating Token Index: 839

Text #16

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0548. Min Act: -0.1700

Data Index: 2654688 (Open Web Text)

Max Activating Token Index: 816

Text #17

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0493. Min Act: -0.1700

Data Index: 4836891 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0631. Min Act: -0.1700

Data Index: 7947839 (Open Web Text)

Max Activating Token Index: 255

Text #19

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.0474. Min Act: -0.1700

Data Index: 8166257 (Open Web Text)

Max Activating Token Index: 373