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

Dataset: Open Web Text

Neuron 2728 in Layer 6

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: 4.9098. Min Range: -4.9098

Max Act: 4.9098. Min Act: -0.1700

Data Index: 4731973 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.6595. Min Act: -0.1700

Data Index: 2428528 (Open Web Text)

Max Activating Token Index: 131

Text #2

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.6090. Min Act: -0.1700

Data Index: 1612774 (Open Web Text)

Max Activating Token Index: 815

Text #3

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.3317. Min Act: -0.1700

Data Index: 1764963 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.2103. Min Act: -0.1700

Data Index: 4983672 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.2484. Min Act: -0.1700

Data Index: 8057328 (Open Web Text)

Max Activating Token Index: 182

Text #6

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.1957. Min Act: -0.1700

Data Index: 6526123 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.1337. Min Act: -0.1700

Data Index: 5498139 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.1075. Min Act: -0.1700

Data Index: 1578658 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 4.9098. Min Range: -4.9098

Max Act: 4.0561. Min Act: -0.1700

Data Index: 3671882 (Open Web Text)

Max Activating Token Index: 577

Text #10

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.9922. Min Act: -0.1700

Data Index: 1412903 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.9774. Min Act: -0.1700

Data Index: 222926 (Open Web Text)

Max Activating Token Index: 126

Text #12

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.9489. Min Act: -0.1700

Data Index: 5888352 (Open Web Text)

Max Activating Token Index: 249

Text #13

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.8019. Min Act: -0.1700

Data Index: 7642251 (Open Web Text)

Max Activating Token Index: 945

Text #14

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.9149. Min Act: -0.1700

Data Index: 6593616 (Open Web Text)

Max Activating Token Index: 281

Text #15

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.8746. Min Act: -0.1700

Data Index: 8195030 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.7403. Min Act: -0.1700

Data Index: 5438793 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.9637. Min Act: -0.1700

Data Index: 1247381 (Open Web Text)

Max Activating Token Index: 611

Text #18

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.8629. Min Act: -0.1700

Data Index: 1077576 (Open Web Text)

Max Activating Token Index: 338

Text #19

Max Range: 4.9098. Min Range: -4.9098

Max Act: 3.8204. Min Act: -0.1700

Data Index: 3730315 (Open Web Text)

Max Activating Token Index: 85