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

Dataset: Open Web Text

Neuron 847 in Layer 4

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: 3.1648. Min Range: -3.1648

Max Act: 3.1363. Min Act: -0.1700

Data Index: 7837182 (Open Web Text)

Max Activating Token Index: 833

Text #1

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1470. Min Act: -0.1700

Data Index: 1432866 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1416. Min Act: -0.1700

Data Index: 7145182 (Open Web Text)

Max Activating Token Index: 571

Text #3

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1648. Min Act: -0.1700

Data Index: 5498810 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1434. Min Act: -0.1700

Data Index: 2909198 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1213. Min Act: -0.1700

Data Index: 8277777 (Open Web Text)

Max Activating Token Index: 53

Text #6

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1202. Min Act: -0.1700

Data Index: 6372590 (Open Web Text)

Max Activating Token Index: 122

Text #7

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1227. Min Act: -0.1700

Data Index: 986760 (Open Web Text)

Max Activating Token Index: 850

Text #8

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1296. Min Act: -0.1700

Data Index: 4898315 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1128. Min Act: -0.1700

Data Index: 1524413 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0829. Min Act: -0.1700

Data Index: 3078219 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1049. Min Act: -0.1700

Data Index: 2014055 (Open Web Text)

Max Activating Token Index: 162

Text #12

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0996. Min Act: -0.1700

Data Index: 8200614 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1086. Min Act: -0.1700

Data Index: 6502016 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0974. Min Act: -0.1700

Data Index: 157456 (Open Web Text)

Max Activating Token Index: 717

Text #15

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0789. Min Act: -0.1700

Data Index: 7095780 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0938. Min Act: -0.1700

Data Index: 7194581 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0841. Min Act: -0.1700

Data Index: 5112865 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1007. Min Act: -0.1700

Data Index: 6134929 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1125. Min Act: -0.1700

Data Index: 6355826 (Open Web Text)

Max Activating Token Index: 395