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

Dataset: Open Web Text

Neuron 2958 in Layer 3

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: 3.2748. Min Range: -3.2748

Max Act: 3.2748. Min Act: -0.1700

Data Index: 4971012 (Open Web Text)

Max Activating Token Index: 473

Text #1

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.2566. Min Act: -0.1700

Data Index: 425619 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.2006. Min Act: -0.1700

Data Index: 6963394 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.2233. Min Act: -0.1700

Data Index: 4321879 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1678. Min Act: -0.1700

Data Index: 2373699 (Open Web Text)

Max Activating Token Index: 963

Text #5

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1588. Min Act: -0.1700

Data Index: 5387896 (Open Web Text)

Max Activating Token Index: 178

Text #6

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1861. Min Act: -0.1700

Data Index: 5396270 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1702. Min Act: -0.1700

Data Index: 8501222 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1651. Min Act: -0.1700

Data Index: 1129000 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1611. Min Act: -0.1700

Data Index: 3550083 (Open Web Text)

Max Activating Token Index: 699

Text #10

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1594. Min Act: -0.1700

Data Index: 4267027 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1621. Min Act: -0.1700

Data Index: 7464778 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1380. Min Act: -0.1700

Data Index: 7207345 (Open Web Text)

Max Activating Token Index: 819

Text #13

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1348. Min Act: -0.1700

Data Index: 7404309 (Open Web Text)

Max Activating Token Index: 796

Text #14

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1697. Min Act: -0.1700

Data Index: 3941855 (Open Web Text)

Max Activating Token Index: 533

Text #15

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1149. Min Act: -0.1700

Data Index: 3046701 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1239. Min Act: -0.1700

Data Index: 394191 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1202. Min Act: -0.1700

Data Index: 7404308 (Open Web Text)

Max Activating Token Index: 274

Text #18

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1257. Min Act: -0.1700

Data Index: 5770828 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 3.2748. Min Range: -3.2748

Max Act: 3.1313. Min Act: -0.1700

Data Index: 6319568 (Open Web Text)

Max Activating Token Index: 640