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

Dataset: Open Web Text

Neuron 1423 in Layer 1

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: 2.0284. Min Range: -2.0284

Max Act: 2.0284. Min Act: -0.1700

Data Index: 7849599 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.9403. Min Act: -0.1700

Data Index: 2013083 (Open Web Text)

Max Activating Token Index: 475

Text #2

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.9041. Min Act: -0.1700

Data Index: 6838197 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.9036. Min Act: -0.1700

Data Index: 8208246 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8803. Min Act: -0.1700

Data Index: 935933 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8777. Min Act: -0.1700

Data Index: 5936051 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8762. Min Act: -0.1700

Data Index: 5381299 (Open Web Text)

Max Activating Token Index: 60

Text #7

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8860. Min Act: -0.1700

Data Index: 7719392 (Open Web Text)

Max Activating Token Index: 437

Text #8

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8731. Min Act: -0.1700

Data Index: 709752 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8822. Min Act: -0.1699

Data Index: 1134772 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8808. Min Act: -0.1700

Data Index: 528655 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8729. Min Act: -0.1700

Data Index: 405553 (Open Web Text)

Max Activating Token Index: 391

Text #12

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8575. Min Act: -0.1700

Data Index: 6752125 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8706. Min Act: -0.1700

Data Index: 2543118 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8642. Min Act: -0.1700

Data Index: 3843913 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8463. Min Act: -0.1700

Data Index: 4492168 (Open Web Text)

Max Activating Token Index: 994

Text #16

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8626. Min Act: -0.1700

Data Index: 2418314 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8505. Min Act: -0.1700

Data Index: 560869 (Open Web Text)

Max Activating Token Index: 76

Text #18

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8496. Min Act: -0.1700

Data Index: 4600890 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 2.0284. Min Range: -2.0284

Max Act: 1.8383. Min Act: -0.1700

Data Index: 5177966 (Open Web Text)

Max Activating Token Index: 43