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

Dataset: Open Web Text

Neuron 1385 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: 4.0675. Min Range: -4.0675

Max Act: 4.0675. Min Act: -0.1700

Data Index: 556728 (Open Web Text)

Max Activating Token Index: 471

Text #1

Max Range: 4.0675. Min Range: -4.0675

Max Act: 4.0633. Min Act: -0.1700

Data Index: 5833463 (Open Web Text)

Max Activating Token Index: 64

Text #2

Max Range: 4.0675. Min Range: -4.0675

Max Act: 4.0252. Min Act: -0.1700

Data Index: 8468227 (Open Web Text)

Max Activating Token Index: 958

Text #3

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9963. Min Act: -0.1700

Data Index: 6000385 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9972. Min Act: -0.1700

Data Index: 2007694 (Open Web Text)

Max Activating Token Index: 870

Text #5

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9634. Min Act: -0.1700

Data Index: 5546810 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9741. Min Act: -0.1700

Data Index: 5791333 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9499. Min Act: -0.1700

Data Index: 4626210 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9507. Min Act: -0.1700

Data Index: 5280572 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9394. Min Act: -0.1700

Data Index: 6228977 (Open Web Text)

Max Activating Token Index: 973

Text #10

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9125. Min Act: -0.1700

Data Index: 1600012 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.8978. Min Act: -0.1700

Data Index: 3813869 (Open Web Text)

Max Activating Token Index: 996

Text #12

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.8822. Min Act: -0.1700

Data Index: 1302219 (Open Web Text)

Max Activating Token Index: 159

Text #13

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.8924. Min Act: -0.1700

Data Index: 1721126 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9003. Min Act: -0.1700

Data Index: 4039885 (Open Web Text)

Max Activating Token Index: 594

Text #15

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9223. Min Act: -0.1700

Data Index: 4225962 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.8948. Min Act: -0.1700

Data Index: 1489134 (Open Web Text)

Max Activating Token Index: 623

Text #17

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.9276. Min Act: -0.1700

Data Index: 2071320 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.8986. Min Act: -0.1700

Data Index: 2868099 (Open Web Text)

Max Activating Token Index: 244

Text #19

Max Range: 4.0675. Min Range: -4.0675

Max Act: 3.8878. Min Act: -0.1700

Data Index: 987147 (Open Web Text)

Max Activating Token Index: 873