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

Dataset: Open Web Text

Neuron 256 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: 4.2890. Min Range: -4.2890

Max Act: 4.2890. Min Act: -0.1700

Data Index: 1862982 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.2734. Min Act: -0.1700

Data Index: 2077384 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.2504. Min Act: -0.1700

Data Index: 5782833 (Open Web Text)

Max Activating Token Index: 654

Text #3

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.2074. Min Act: -0.1700

Data Index: 2291812 (Open Web Text)

Max Activating Token Index: 461

Text #4

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.1747. Min Act: -0.1700

Data Index: 4669707 (Open Web Text)

Max Activating Token Index: 246

Text #5

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.1625. Min Act: -0.1700

Data Index: 4507699 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.1418. Min Act: -0.1700

Data Index: 1595414 (Open Web Text)

Max Activating Token Index: 31

Text #7

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.1152. Min Act: -0.1700

Data Index: 849179 (Open Web Text)

Max Activating Token Index: 338

Text #8

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.1102. Min Act: -0.1700

Data Index: 869472 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.1017. Min Act: -0.1700

Data Index: 2627248 (Open Web Text)

Max Activating Token Index: 727

Text #10

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0859. Min Act: -0.1700

Data Index: 501781 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0738. Min Act: -0.1700

Data Index: 5076898 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0984. Min Act: -0.1700

Data Index: 288088 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0800. Min Act: -0.1700

Data Index: 288089 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0856. Min Act: -0.1700

Data Index: 2089334 (Open Web Text)

Max Activating Token Index: 150

Text #15

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0754. Min Act: -0.1700

Data Index: 396089 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0631. Min Act: -0.1700

Data Index: 6995101 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0786. Min Act: -0.1700

Data Index: 2389951 (Open Web Text)

Max Activating Token Index: 447

Text #18

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0689. Min Act: -0.1700

Data Index: 1241188 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 4.2890. Min Range: -4.2890

Max Act: 4.0943. Min Act: -0.1700

Data Index: 7217733 (Open Web Text)

Max Activating Token Index: 1015