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

Dataset: Open Web Text

Neuron 1036 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: 5.6058. Min Range: -5.6058

Max Act: 5.6058. Min Act: -0.1700

Data Index: 5869708 (Open Web Text)

Max Activating Token Index: 707

Text #1

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.5331. Min Act: -0.1700

Data Index: 6660942 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4988. Min Act: -0.1700

Data Index: 4668462 (Open Web Text)

Max Activating Token Index: 346

Text #3

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.5086. Min Act: -0.1700

Data Index: 6241358 (Open Web Text)

Max Activating Token Index: 635

Text #4

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4807. Min Act: -0.1700

Data Index: 1257314 (Open Web Text)

Max Activating Token Index: 209

Text #5

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4647. Min Act: -0.1700

Data Index: 1109902 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4585. Min Act: -0.1700

Data Index: 7582876 (Open Web Text)

Max Activating Token Index: 796

Text #7

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4642. Min Act: -0.1700

Data Index: 6331432 (Open Web Text)

Max Activating Token Index: 694

Text #8

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4749. Min Act: -0.1700

Data Index: 8391727 (Open Web Text)

Max Activating Token Index: 406

Text #9

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4792. Min Act: -0.1700

Data Index: 4269533 (Open Web Text)

Max Activating Token Index: 447

Text #10

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4536. Min Act: -0.1700

Data Index: 2589084 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4101. Min Act: -0.1700

Data Index: 8453046 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.3979. Min Act: -0.1700

Data Index: 2939324 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.4309. Min Act: -0.1700

Data Index: 2873075 (Open Web Text)

Max Activating Token Index: 179

Text #14

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.3710. Min Act: -0.1700

Data Index: 7627883 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.3928. Min Act: -0.1700

Data Index: 7666252 (Open Web Text)

Max Activating Token Index: 166

Text #16

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.3829. Min Act: -0.1700

Data Index: 6307503 (Open Web Text)

Max Activating Token Index: 871

Text #17

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.3604. Min Act: -0.1700

Data Index: 8042522 (Open Web Text)

Max Activating Token Index: 775

Text #18

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.3445. Min Act: -0.1700

Data Index: 3663530 (Open Web Text)

Max Activating Token Index: 327

Text #19

Max Range: 5.6058. Min Range: -5.6058

Max Act: 5.3585. Min Act: -0.1700

Data Index: 3354280 (Open Web Text)

Max Activating Token Index: 279