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

Dataset: Open Web Text

Neuron 1511 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: 1.6591. Min Range: -1.6591

Max Act: 1.6591. Min Act: -0.1700

Data Index: 3283915 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6400. Min Act: -0.1696

Data Index: 8502834 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6454. Min Act: -0.1700

Data Index: 707406 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6333. Min Act: -0.1700

Data Index: 467655 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6259. Min Act: -0.1700

Data Index: 5365591 (Open Web Text)

Max Activating Token Index: 128

Text #5

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6134. Min Act: -0.1700

Data Index: 7416882 (Open Web Text)

Max Activating Token Index: 183

Text #6

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6105. Min Act: -0.1700

Data Index: 5698096 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6102. Min Act: -0.1699

Data Index: 5568228 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6140. Min Act: -0.1700

Data Index: 1384449 (Open Web Text)

Max Activating Token Index: 964

Text #9

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5970. Min Act: -0.1700

Data Index: 2152986 (Open Web Text)

Max Activating Token Index: 462

Text #10

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5998. Min Act: -0.1700

Data Index: 4150255 (Open Web Text)

Max Activating Token Index: 511

Text #11

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6002. Min Act: -0.1700

Data Index: 574207 (Open Web Text)

Max Activating Token Index: 692

Text #12

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5966. Min Act: -0.1700

Data Index: 1967640 (Open Web Text)

Max Activating Token Index: 160

Text #13

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5764. Min Act: -0.1683

Data Index: 8197999 (Open Web Text)

Max Activating Token Index: 656

Text #14

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5788. Min Act: -0.1700

Data Index: 919776 (Open Web Text)

Max Activating Token Index: 375

Text #15

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5758. Min Act: -0.1698

Data Index: 378069 (Open Web Text)

Max Activating Token Index: 342

Text #16

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5705. Min Act: -0.1700

Data Index: 2224370 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5673. Min Act: -0.1700

Data Index: 5465781 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5704. Min Act: -0.1700

Data Index: 2827797 (Open Web Text)

Max Activating Token Index: 132

Text #19

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.5746. Min Act: -0.1700

Data Index: 2666218 (Open Web Text)

Max Activating Token Index: 157