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

Dataset: Open Web Text

Neuron 541 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: 2.4234. Min Range: -2.4234

Max Act: 2.4234. Min Act: -0.1700

Data Index: 5531747 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.2592. Min Act: -0.1700

Data Index: 8047752 (Open Web Text)

Max Activating Token Index: 975

Text #2

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.2168. Min Act: -0.1698

Data Index: 6119588 (Open Web Text)

Max Activating Token Index: 39

Text #3

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.1719. Min Act: -0.1700

Data Index: 8693137 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.2122. Min Act: -0.1700

Data Index: 1332672 (Open Web Text)

Max Activating Token Index: 789

Text #5

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.2067. Min Act: -0.1700

Data Index: 2274958 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.1582. Min Act: -0.1700

Data Index: 4551137 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.1583. Min Act: -0.1700

Data Index: 2078491 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.1680. Min Act: -0.1700

Data Index: 3078174 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.1565. Min Act: -0.1700

Data Index: 7601882 (Open Web Text)

Max Activating Token Index: 261

Text #10

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.1228. Min Act: -0.1700

Data Index: 1127552 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.1287. Min Act: -0.1698

Data Index: 5242595 (Open Web Text)

Max Activating Token Index: 956

Text #12

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.0904. Min Act: -0.1700

Data Index: 3106195 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.0802. Min Act: -0.1700

Data Index: 4813207 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.0866. Min Act: -0.1700

Data Index: 2492415 (Open Web Text)

Max Activating Token Index: 957

Text #15

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.0896. Min Act: -0.1700

Data Index: 5473210 (Open Web Text)

Max Activating Token Index: 485

Text #16

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.0926. Min Act: -0.1700

Data Index: 5531746 (Open Web Text)

Max Activating Token Index: 920

Text #17

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.0866. Min Act: -0.1700

Data Index: 7310792 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.0674. Min Act: -0.1698

Data Index: 7806154 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 2.4234. Min Range: -2.4234

Max Act: 2.0851. Min Act: -0.1700

Data Index: 2029391 (Open Web Text)

Max Activating Token Index: 777