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

Dataset: Open Web Text

Neuron 535 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: 2.1979. Min Range: -2.1979

Max Act: 2.1979. Min Act: -0.1700

Data Index: 6826555 (Open Web Text)

Max Activating Token Index: 476

Text #1

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1810. Min Act: -0.1700

Data Index: 224548 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1521. Min Act: -0.1700

Data Index: 4865072 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1526. Min Act: -0.1700

Data Index: 5935013 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1373. Min Act: -0.1700

Data Index: 7564362 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1235. Min Act: -0.1700

Data Index: 1150660 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1279. Min Act: -0.1700

Data Index: 2516201 (Open Web Text)

Max Activating Token Index: 1011

Text #7

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1246. Min Act: -0.1700

Data Index: 3812226 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1157. Min Act: -0.1700

Data Index: 8023172 (Open Web Text)

Max Activating Token Index: 799

Text #9

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1013. Min Act: -0.1700

Data Index: 3812225 (Open Web Text)

Max Activating Token Index: 216

Text #10

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.1057. Min Act: -0.1700

Data Index: 3788103 (Open Web Text)

Max Activating Token Index: 68

Text #11

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0719. Min Act: -0.1700

Data Index: 4225078 (Open Web Text)

Max Activating Token Index: 773

Text #12

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0677. Min Act: -0.1700

Data Index: 7639471 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0730. Min Act: -0.1700

Data Index: 19604 (Open Web Text)

Max Activating Token Index: 595

Text #14

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0874. Min Act: -0.1700

Data Index: 947282 (Open Web Text)

Max Activating Token Index: 136

Text #15

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0618. Min Act: -0.1700

Data Index: 1609534 (Open Web Text)

Max Activating Token Index: 974

Text #16

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0634. Min Act: -0.1700

Data Index: 4891452 (Open Web Text)

Max Activating Token Index: 718

Text #17

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0589. Min Act: -0.1700

Data Index: 440396 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0632. Min Act: -0.1700

Data Index: 2956446 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 2.1979. Min Range: -2.1979

Max Act: 2.0617. Min Act: -0.1700

Data Index: 7229893 (Open Web Text)

Max Activating Token Index: 130