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

Dataset: Open Web Text

Neuron 2501 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: 4.5811. Min Range: -4.5811

Max Act: 4.5811. Min Act: -0.1700

Data Index: 8788776 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.5225. Min Act: -0.1700

Data Index: 2979760 (Open Web Text)

Max Activating Token Index: 876

Text #2

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.5118. Min Act: -0.1700

Data Index: 7675660 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.4766. Min Act: -0.1700

Data Index: 4103548 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.4896. Min Act: -0.1700

Data Index: 2007163 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.4322. Min Act: -0.1700

Data Index: 4103549 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.4213. Min Act: -0.1700

Data Index: 843366 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.4119. Min Act: -0.1700

Data Index: 2141899 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3871. Min Act: -0.1700

Data Index: 3773171 (Open Web Text)

Max Activating Token Index: 678

Text #9

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.4002. Min Act: -0.1700

Data Index: 1443810 (Open Web Text)

Max Activating Token Index: 478

Text #10

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3824. Min Act: -0.1700

Data Index: 5450021 (Open Web Text)

Max Activating Token Index: 839

Text #11

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3879. Min Act: -0.1700

Data Index: 1893246 (Open Web Text)

Max Activating Token Index: 531

Text #12

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3584. Min Act: -0.1700

Data Index: 1326160 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.4037. Min Act: -0.1700

Data Index: 4749602 (Open Web Text)

Max Activating Token Index: 911

Text #14

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3767. Min Act: -0.1700

Data Index: 519404 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3605. Min Act: -0.1700

Data Index: 7016037 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3337. Min Act: -0.1700

Data Index: 6606777 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3690. Min Act: -0.1700

Data Index: 6269334 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3342. Min Act: -0.1700

Data Index: 6148693 (Open Web Text)

Max Activating Token Index: 796

Text #19

Max Range: 4.5811. Min Range: -4.5811

Max Act: 4.3473. Min Act: -0.1700

Data Index: 8053933 (Open Web Text)

Max Activating Token Index: 259