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

Dataset: Open Web Text

Neuron 2137 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: 1.8095. Min Range: -1.8095

Max Act: 1.8095. Min Act: -0.1700

Data Index: 7178354 (Open Web Text)

Max Activating Token Index: 887

Text #1

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.7289. Min Act: -0.1700

Data Index: 8693357 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.7144. Min Act: -0.1700

Data Index: 4300077 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.7148. Min Act: -0.1699

Data Index: 8536745 (Open Web Text)

Max Activating Token Index: 401

Text #4

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.7071. Min Act: -0.1700

Data Index: 5695064 (Open Web Text)

Max Activating Token Index: 83

Text #5

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.7030. Min Act: -0.1700

Data Index: 6146936 (Open Web Text)

Max Activating Token Index: 174

Text #6

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.7007. Min Act: -0.1700

Data Index: 2894797 (Open Web Text)

Max Activating Token Index: 858

Text #7

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6843. Min Act: -0.1700

Data Index: 7432991 (Open Web Text)

Max Activating Token Index: 738

Text #8

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6816. Min Act: -0.1700

Data Index: 4952245 (Open Web Text)

Max Activating Token Index: 853

Text #9

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6890. Min Act: -0.1700

Data Index: 3759341 (Open Web Text)

Max Activating Token Index: 707

Text #10

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6751. Min Act: -0.1700

Data Index: 159499 (Open Web Text)

Max Activating Token Index: 60

Text #11

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6736. Min Act: -0.1700

Data Index: 3791456 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6719. Min Act: -0.1700

Data Index: 1583220 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6786. Min Act: -0.1700

Data Index: 5447137 (Open Web Text)

Max Activating Token Index: 119

Text #14

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6689. Min Act: -0.1700

Data Index: 2843156 (Open Web Text)

Max Activating Token Index: 572

Text #15

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6617. Min Act: -0.1700

Data Index: 3895153 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6714. Min Act: -0.1700

Data Index: 8448901 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6580. Min Act: -0.1700

Data Index: 6424129 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6670. Min Act: -0.1700

Data Index: 8365260 (Open Web Text)

Max Activating Token Index: 605

Text #19

Max Range: 1.8095. Min Range: -1.8095

Max Act: 1.6560. Min Act: -0.1700

Data Index: 378032 (Open Web Text)

Max Activating Token Index: 190