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

Dataset: Open Web Text

Neuron 2665 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: 1.6629. Min Range: -1.6629

Max Act: 1.6617. Min Act: -0.1700

Data Index: 1547154 (Open Web Text)

Max Activating Token Index: 802

Text #1

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.6629. Min Act: -0.1700

Data Index: 1547155 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.6111. Min Act: -0.1700

Data Index: 1547153 (Open Web Text)

Max Activating Token Index: 870

Text #3

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.5569. Min Act: -0.1700

Data Index: 1547156 (Open Web Text)

Max Activating Token Index: 812

Text #4

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.4154. Min Act: -0.1700

Data Index: 8570899 (Open Web Text)

Max Activating Token Index: 809

Text #5

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.3823. Min Act: -0.1700

Data Index: 7310764 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.3668. Min Act: -0.1700

Data Index: 5951941 (Open Web Text)

Max Activating Token Index: 764

Text #7

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.3341. Min Act: -0.1700

Data Index: 2331832 (Open Web Text)

Max Activating Token Index: 881

Text #8

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.3343. Min Act: -0.1700

Data Index: 264413 (Open Web Text)

Max Activating Token Index: 725

Text #9

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.3310. Min Act: -0.1700

Data Index: 345147 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.3041. Min Act: -0.1700

Data Index: 3917742 (Open Web Text)

Max Activating Token Index: 708

Text #11

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2914. Min Act: -0.1700

Data Index: 3635721 (Open Web Text)

Max Activating Token Index: 390

Text #12

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2947. Min Act: -0.1700

Data Index: 7417162 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2967. Min Act: -0.1700

Data Index: 8069108 (Open Web Text)

Max Activating Token Index: 778

Text #14

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2837. Min Act: -0.1700

Data Index: 6131505 (Open Web Text)

Max Activating Token Index: 771

Text #15

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2824. Min Act: -0.1700

Data Index: 7310765 (Open Web Text)

Max Activating Token Index: 974

Text #16

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2586. Min Act: -0.1700

Data Index: 5897902 (Open Web Text)

Max Activating Token Index: 711

Text #17

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2791. Min Act: -0.1700

Data Index: 130332 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2730. Min Act: -0.1700

Data Index: 3227422 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 1.6629. Min Range: -1.6629

Max Act: 1.2716. Min Act: -0.1700

Data Index: 8101900 (Open Web Text)

Max Activating Token Index: 889