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

Dataset: Open Web Text

Neuron 2255 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: 1.9312. Min Range: -1.9312

Max Act: 1.9312. Min Act: -0.1700

Data Index: 5775866 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.9177. Min Act: -0.1700

Data Index: 7848453 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8843. Min Act: -0.1700

Data Index: 8722111 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8828. Min Act: -0.1700

Data Index: 6091062 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8742. Min Act: -0.1700

Data Index: 7674446 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8739. Min Act: -0.1700

Data Index: 963012 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8769. Min Act: -0.1700

Data Index: 1398589 (Open Web Text)

Max Activating Token Index: 177

Text #7

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8427. Min Act: -0.1700

Data Index: 8811480 (Open Web Text)

Max Activating Token Index: 99

Text #8

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8363. Min Act: -0.1700

Data Index: 6301139 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8477. Min Act: -0.1700

Data Index: 1169775 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8387. Min Act: -0.1700

Data Index: 4762530 (Open Web Text)

Max Activating Token Index: 144

Text #11

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8411. Min Act: -0.1700

Data Index: 6772631 (Open Web Text)

Max Activating Token Index: 504

Text #12

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8102. Min Act: -0.1700

Data Index: 6114491 (Open Web Text)

Max Activating Token Index: 223

Text #13

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8218. Min Act: -0.1700

Data Index: 8230149 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8077. Min Act: -0.1700

Data Index: 5934652 (Open Web Text)

Max Activating Token Index: 707

Text #15

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8152. Min Act: -0.1700

Data Index: 3430281 (Open Web Text)

Max Activating Token Index: 549

Text #16

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8246. Min Act: -0.1700

Data Index: 759478 (Open Web Text)

Max Activating Token Index: 595

Text #17

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8205. Min Act: -0.1700

Data Index: 6943833 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8159. Min Act: -0.1700

Data Index: 5260698 (Open Web Text)

Max Activating Token Index: 993

Text #19

Max Range: 1.9312. Min Range: -1.9312

Max Act: 1.8136. Min Act: -0.1700

Data Index: 6567317 (Open Web Text)

Max Activating Token Index: 545