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

Dataset: Open Web Text

Neuron 2854 in Layer 0

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: 3.6008. Min Range: -3.6008

Max Act: 3.6008. Min Act: -0.1700

Data Index: 7716522 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.6008. Min Act: -0.1700

Data Index: 4831947 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.6008. Min Act: -0.1700

Data Index: 4915911 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.6008. Min Act: -0.1700

Data Index: 336893 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4967. Min Act: -0.1700

Data Index: 3130973 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.5142. Min Act: -0.1700

Data Index: 7506878 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4923. Min Act: -0.1700

Data Index: 2327737 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4911. Min Act: -0.1700

Data Index: 7366087 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4789. Min Act: -0.1700

Data Index: 4997956 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4789. Min Act: -0.1700

Data Index: 5316770 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4716. Min Act: -0.1700

Data Index: 4974831 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4778. Min Act: -0.1700

Data Index: 4007872 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4797. Min Act: -0.1700

Data Index: 1600900 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4792. Min Act: -0.1700

Data Index: 6694490 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1248763 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4603. Min Act: -0.1700

Data Index: 1039607 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4582. Min Act: -0.1700

Data Index: 3307555 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4607. Min Act: -0.1700

Data Index: 8351558 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4499. Min Act: -0.1700

Data Index: 1781007 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.6008. Min Range: -3.6008

Max Act: 3.4357. Min Act: -0.1700

Data Index: 2761455 (Open Web Text)

Max Activating Token Index: 8