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

Dataset: Open Web Text

Neuron 1887 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: 5.0984. Min Range: -5.0984

Max Act: 5.0984. Min Act: -0.1700

Data Index: 8803586 (Open Web Text)

Max Activating Token Index: 899

Text #1

Max Range: 5.0984. Min Range: -5.0984

Max Act: 5.0521. Min Act: -0.1700

Data Index: 6395724 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 5.0984. Min Range: -5.0984

Max Act: 5.0158. Min Act: -0.1700

Data Index: 584982 (Open Web Text)

Max Activating Token Index: 703

Text #3

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.9947. Min Act: -0.1700

Data Index: 4556964 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.9406. Min Act: -0.1700

Data Index: 5931607 (Open Web Text)

Max Activating Token Index: 843

Text #5

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.9212. Min Act: -0.1700

Data Index: 2885218 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.9145. Min Act: -0.1700

Data Index: 4852664 (Open Web Text)

Max Activating Token Index: 893

Text #7

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.9284. Min Act: -0.1700

Data Index: 1313217 (Open Web Text)

Max Activating Token Index: 539

Text #8

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.9129. Min Act: -0.1700

Data Index: 2500245 (Open Web Text)

Max Activating Token Index: 794

Text #9

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8838. Min Act: -0.1700

Data Index: 2976183 (Open Web Text)

Max Activating Token Index: 1006

Text #10

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8872. Min Act: -0.1700

Data Index: 5338137 (Open Web Text)

Max Activating Token Index: 964

Text #11

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8494. Min Act: -0.1700

Data Index: 993477 (Open Web Text)

Max Activating Token Index: 610

Text #12

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8463. Min Act: -0.1700

Data Index: 7967515 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.7903. Min Act: -0.1700

Data Index: 4814901 (Open Web Text)

Max Activating Token Index: 92

Text #14

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8065. Min Act: -0.1700

Data Index: 2129947 (Open Web Text)

Max Activating Token Index: 91

Text #15

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8098. Min Act: -0.1700

Data Index: 6993739 (Open Web Text)

Max Activating Token Index: 311

Text #16

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.7733. Min Act: -0.1700

Data Index: 8150239 (Open Web Text)

Max Activating Token Index: 472

Text #17

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.7951. Min Act: -0.1700

Data Index: 6957194 (Open Web Text)

Max Activating Token Index: 464

Text #18

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.7668. Min Act: -0.1700

Data Index: 4164029 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.7830. Min Act: -0.1700

Data Index: 2514584 (Open Web Text)

Max Activating Token Index: 283