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

Dataset: Open Web Text

Neuron 2841 in Layer 6

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: 5.2589. Min Range: -5.2589

Max Act: 5.2589. Min Act: -0.1700

Data Index: 4116789 (Open Web Text)

Max Activating Token Index: 693

Text #1

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.1937. Min Act: -0.1700

Data Index: 1421818 (Open Web Text)

Max Activating Token Index: 862

Text #2

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.1973. Min Act: -0.1700

Data Index: 1088693 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.1589. Min Act: -0.1700

Data Index: 4243471 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.1619. Min Act: -0.1700

Data Index: 3929770 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.1730. Min Act: -0.1700

Data Index: 4676589 (Open Web Text)

Max Activating Token Index: 317

Text #6

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.1224. Min Act: -0.1700

Data Index: 1672819 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.1215. Min Act: -0.1700

Data Index: 7718801 (Open Web Text)

Max Activating Token Index: 464

Text #8

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0903. Min Act: -0.1700

Data Index: 295203 (Open Web Text)

Max Activating Token Index: 995

Text #9

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0711. Min Act: -0.1700

Data Index: 7826598 (Open Web Text)

Max Activating Token Index: 770

Text #10

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0895. Min Act: -0.1700

Data Index: 7757500 (Open Web Text)

Max Activating Token Index: 945

Text #11

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0758. Min Act: -0.1700

Data Index: 4868260 (Open Web Text)

Max Activating Token Index: 951

Text #12

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0781. Min Act: -0.1700

Data Index: 3580936 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0856. Min Act: -0.1700

Data Index: 784195 (Open Web Text)

Max Activating Token Index: 126

Text #14

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0524. Min Act: -0.1700

Data Index: 5289037 (Open Web Text)

Max Activating Token Index: 639

Text #15

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0675. Min Act: -0.1700

Data Index: 2834323 (Open Web Text)

Max Activating Token Index: 236

Text #16

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0286. Min Act: -0.1700

Data Index: 763224 (Open Web Text)

Max Activating Token Index: 374

Text #17

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0016. Min Act: -0.1700

Data Index: 7752030 (Open Web Text)

Max Activating Token Index: 269

Text #18

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0320. Min Act: -0.1700

Data Index: 6702211 (Open Web Text)

Max Activating Token Index: 268

Text #19

Max Range: 5.2589. Min Range: -5.2589

Max Act: 5.0214. Min Act: -0.1700

Data Index: 2862756 (Open Web Text)

Max Activating Token Index: 343