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

Dataset: Open Web Text

Neuron 938 in Layer 3

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: 3.5898. Min Range: -3.5898

Max Act: 3.5898. Min Act: -0.1700

Data Index: 3164568 (Open Web Text)

Max Activating Token Index: 279

Text #1

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4569. Min Act: -0.1700

Data Index: 4935590 (Open Web Text)

Max Activating Token Index: 593

Text #2

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4399. Min Act: -0.1700

Data Index: 3726965 (Open Web Text)

Max Activating Token Index: 554

Text #3

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4323. Min Act: -0.1700

Data Index: 4732850 (Open Web Text)

Max Activating Token Index: 898

Text #4

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4041. Min Act: -0.1700

Data Index: 1421302 (Open Web Text)

Max Activating Token Index: 1007

Text #5

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1595778 (Open Web Text)

Max Activating Token Index: 669

Text #6

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4083. Min Act: -0.1700

Data Index: 6773900 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4273. Min Act: -0.1700

Data Index: 4379679 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4128. Min Act: -0.1700

Data Index: 7564031 (Open Web Text)

Max Activating Token Index: 338

Text #9

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4398. Min Act: -0.1700

Data Index: 4626607 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4303. Min Act: -0.1700

Data Index: 6486987 (Open Web Text)

Max Activating Token Index: 663

Text #11

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4065. Min Act: -0.1700

Data Index: 123424 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4178. Min Act: -0.1700

Data Index: 6805404 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3804. Min Act: -0.1700

Data Index: 7727636 (Open Web Text)

Max Activating Token Index: 206

Text #14

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4089. Min Act: -0.1700

Data Index: 4935453 (Open Web Text)

Max Activating Token Index: 688

Text #15

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3918. Min Act: -0.1700

Data Index: 6692330 (Open Web Text)

Max Activating Token Index: 1008

Text #16

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3781. Min Act: -0.1700

Data Index: 6093913 (Open Web Text)

Max Activating Token Index: 846

Text #17

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4188. Min Act: -0.1700

Data Index: 5149647 (Open Web Text)

Max Activating Token Index: 844

Text #18

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3908. Min Act: -0.1700

Data Index: 4933298 (Open Web Text)

Max Activating Token Index: 830

Text #19

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3805. Min Act: -0.1700

Data Index: 927657 (Open Web Text)

Max Activating Token Index: 315