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

Dataset: Open Web Text

Neuron 2634 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: 4.9253. Min Range: -4.9253

Max Act: 4.9253. Min Act: -0.1700

Data Index: 5705860 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.8150. Min Act: -0.1700

Data Index: 2110968 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.7576. Min Act: -0.1700

Data Index: 7092757 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.7559. Min Act: -0.1700

Data Index: 3811015 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.7294. Min Act: -0.1700

Data Index: 5605824 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6720. Min Act: -0.1700

Data Index: 6932262 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6757. Min Act: -0.1700

Data Index: 4268938 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6807. Min Act: -0.1700

Data Index: 6998905 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6728. Min Act: -0.1700

Data Index: 4139700 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6838. Min Act: -0.1700

Data Index: 6057819 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6912. Min Act: -0.1700

Data Index: 7238325 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6691. Min Act: -0.1700

Data Index: 6216682 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6578. Min Act: -0.1700

Data Index: 6152005 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6485. Min Act: -0.1700

Data Index: 4184463 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6538. Min Act: -0.1700

Data Index: 3779698 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6530. Min Act: -0.1700

Data Index: 1570026 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6471. Min Act: -0.1700

Data Index: 7086551 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6127. Min Act: -0.1700

Data Index: 5959927 (Open Web Text)

Max Activating Token Index: 833

Text #18

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6391. Min Act: -0.1700

Data Index: 5338391 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.9253. Min Range: -4.9253

Max Act: 4.6705. Min Act: -0.1700

Data Index: 2304929 (Open Web Text)

Max Activating Token Index: 8