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

Dataset: Open Web Text

Neuron 2749 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: 1.7235. Min Range: -1.7235

Max Act: 1.7235. Min Act: -0.1700

Data Index: 2923978 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.6959. Min Act: -0.1700

Data Index: 1827579 (Open Web Text)

Max Activating Token Index: 573

Text #2

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.6714. Min Act: -0.1700

Data Index: 6037360 (Open Web Text)

Max Activating Token Index: 673

Text #3

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.6387. Min Act: -0.1700

Data Index: 4362700 (Open Web Text)

Max Activating Token Index: 224

Text #4

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.6066. Min Act: -0.1700

Data Index: 1402324 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5934. Min Act: -0.1700

Data Index: 4014143 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5867. Min Act: -0.1700

Data Index: 8471537 (Open Web Text)

Max Activating Token Index: 611

Text #7

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5933. Min Act: -0.1700

Data Index: 641264 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5800. Min Act: -0.1697

Data Index: 6578647 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5733. Min Act: -0.1700

Data Index: 5126957 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5753. Min Act: -0.1700

Data Index: 4797896 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5748. Min Act: -0.1700

Data Index: 8530158 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5646. Min Act: -0.1700

Data Index: 7824125 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5570. Min Act: -0.1700

Data Index: 5139444 (Open Web Text)

Max Activating Token Index: 882

Text #14

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5417. Min Act: -0.1700

Data Index: 5391020 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5466. Min Act: -0.1700

Data Index: 4087190 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5430. Min Act: -0.1700

Data Index: 6589099 (Open Web Text)

Max Activating Token Index: 170

Text #17

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5498. Min Act: -0.1700

Data Index: 7043604 (Open Web Text)

Max Activating Token Index: 932

Text #18

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5412. Min Act: -0.1700

Data Index: 730750 (Open Web Text)

Max Activating Token Index: 427

Text #19

Max Range: 1.7235. Min Range: -1.7235

Max Act: 1.5469. Min Act: -0.1700

Data Index: 7664232 (Open Web Text)

Max Activating Token Index: 911