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

Dataset: Open Web Text

Neuron 697 in Layer 5

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: 2.1897. Min Range: -2.1897

Max Act: 2.1897. Min Act: -0.1700

Data Index: 5912799 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.1281. Min Act: -0.1700

Data Index: 943255 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.1273. Min Act: -0.1700

Data Index: 6331859 (Open Web Text)

Max Activating Token Index: 992

Text #3

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.1291. Min Act: -0.1700

Data Index: 658800 (Open Web Text)

Max Activating Token Index: 379

Text #4

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0992. Min Act: -0.1700

Data Index: 8607891 (Open Web Text)

Max Activating Token Index: 789

Text #5

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0979. Min Act: -0.1700

Data Index: 3273774 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.1128. Min Act: -0.1700

Data Index: 629716 (Open Web Text)

Max Activating Token Index: 780

Text #7

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0809. Min Act: -0.1700

Data Index: 6669874 (Open Web Text)

Max Activating Token Index: 233

Text #8

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.1115. Min Act: -0.1700

Data Index: 2500914 (Open Web Text)

Max Activating Token Index: 456

Text #9

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0647. Min Act: -0.1700

Data Index: 4194925 (Open Web Text)

Max Activating Token Index: 959

Text #10

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0641. Min Act: -0.1700

Data Index: 6839629 (Open Web Text)

Max Activating Token Index: 968

Text #11

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0594. Min Act: -0.1700

Data Index: 1233963 (Open Web Text)

Max Activating Token Index: 974

Text #12

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0621. Min Act: -0.1700

Data Index: 7652134 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0677. Min Act: -0.1700

Data Index: 2270776 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0369. Min Act: -0.1700

Data Index: 3490707 (Open Web Text)

Max Activating Token Index: 279

Text #15

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0310. Min Act: -0.1700

Data Index: 2076157 (Open Web Text)

Max Activating Token Index: 980

Text #16

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0276. Min Act: -0.1700

Data Index: 4469030 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0260. Min Act: -0.1700

Data Index: 377785 (Open Web Text)

Max Activating Token Index: 891

Text #18

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0247. Min Act: -0.1700

Data Index: 7149687 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0118. Min Act: -0.1700

Data Index: 1427396 (Open Web Text)

Max Activating Token Index: 147