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

Dataset: Open Web Text

Neuron 2534 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: 1.7251. Min Range: -1.7251

Max Act: 1.7251. Min Act: -0.1700

Data Index: 2476806 (Open Web Text)

Max Activating Token Index: 223

Text #1

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.6391. Min Act: -0.1699

Data Index: 6848066 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.6193. Min Act: -0.1700

Data Index: 7167360 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5981. Min Act: -0.1700

Data Index: 7307626 (Open Web Text)

Max Activating Token Index: 92

Text #4

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5856. Min Act: -0.1700

Data Index: 3732204 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5921. Min Act: -0.1700

Data Index: 8714448 (Open Web Text)

Max Activating Token Index: 99

Text #6

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5909. Min Act: -0.1700

Data Index: 2113895 (Open Web Text)

Max Activating Token Index: 126

Text #7

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5976. Min Act: -0.1700

Data Index: 3098772 (Open Web Text)

Max Activating Token Index: 329

Text #8

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5809. Min Act: -0.1700

Data Index: 5870380 (Open Web Text)

Max Activating Token Index: 646

Text #9

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5715. Min Act: -0.1700

Data Index: 2379300 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5729. Min Act: -0.1700

Data Index: 4174789 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5683. Min Act: -0.1700

Data Index: 8279486 (Open Web Text)

Max Activating Token Index: 47

Text #12

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5874. Min Act: -0.1700

Data Index: 4941514 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5739. Min Act: -0.1700

Data Index: 7010109 (Open Web Text)

Max Activating Token Index: 46

Text #14

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5719. Min Act: -0.1700

Data Index: 4766888 (Open Web Text)

Max Activating Token Index: 951

Text #15

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5696. Min Act: -0.1700

Data Index: 3038754 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5599. Min Act: -0.1700

Data Index: 612192 (Open Web Text)

Max Activating Token Index: 265

Text #17

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5508. Min Act: -0.1700

Data Index: 2847884 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5626. Min Act: -0.1700

Data Index: 1441872 (Open Web Text)

Max Activating Token Index: 688

Text #19

Max Range: 1.7251. Min Range: -1.7251

Max Act: 1.5626. Min Act: -0.1700

Data Index: 5522529 (Open Web Text)

Max Activating Token Index: 163