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

Dataset: Open Web Text

Neuron 3010 in Layer 0

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: 1.7504. Min Range: -1.7504

Max Act: 1.7504. Min Act: -0.1696

Data Index: 3323018 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.7383. Min Act: -0.1652

Data Index: 5457780 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.7299. Min Act: -0.1700

Data Index: 7864216 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.7045. Min Act: -0.1664

Data Index: 6343545 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6934. Min Act: -0.1688

Data Index: 5043501 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6956. Min Act: -0.1700

Data Index: 5700101 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6970. Min Act: -0.1698

Data Index: 8217465 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6878. Min Act: -0.1643

Data Index: 7051904 (Open Web Text)

Max Activating Token Index: 812

Text #8

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6809. Min Act: -0.1696

Data Index: 7201338 (Open Web Text)

Max Activating Token Index: 886

Text #9

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6688. Min Act: -0.1691

Data Index: 2249595 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6736. Min Act: -0.1697

Data Index: 1343096 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6673. Min Act: -0.1700

Data Index: 488770 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6560. Min Act: -0.1700

Data Index: 4202291 (Open Web Text)

Max Activating Token Index: 629

Text #13

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6622. Min Act: -0.1677

Data Index: 8293447 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6552. Min Act: -0.1700

Data Index: 4618234 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6476. Min Act: -0.1599

Data Index: 4947003 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6480. Min Act: -0.1699

Data Index: 5885473 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6498. Min Act: -0.1698

Data Index: 8174066 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6541. Min Act: -0.1684

Data Index: 3359790 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.7504. Min Range: -1.7504

Max Act: 1.6541. Min Act: -0.1700

Data Index: 1098733 (Open Web Text)

Max Activating Token Index: 2