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

Dataset: Open Web Text

Neuron 1830 in Layer 5

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: 4.2906. Min Range: -4.2906

Max Act: 4.2906. Min Act: -0.1700

Data Index: 5603302 (Open Web Text)

Max Activating Token Index: 498

Text #1

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.2745. Min Act: -0.1700

Data Index: 7675739 (Open Web Text)

Max Activating Token Index: 591

Text #2

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.2462. Min Act: -0.1700

Data Index: 6717057 (Open Web Text)

Max Activating Token Index: 563

Text #3

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.2540. Min Act: -0.1700

Data Index: 5490790 (Open Web Text)

Max Activating Token Index: 247

Text #4

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.2196. Min Act: -0.1700

Data Index: 3618831 (Open Web Text)

Max Activating Token Index: 665

Text #5

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1812. Min Act: -0.1700

Data Index: 8364169 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.2230. Min Act: -0.1700

Data Index: 6630974 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.2064. Min Act: -0.1700

Data Index: 2063392 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1722. Min Act: -0.1700

Data Index: 2595441 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1825. Min Act: -0.1700

Data Index: 3146481 (Open Web Text)

Max Activating Token Index: 283

Text #10

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1725. Min Act: -0.1700

Data Index: 7641108 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1640. Min Act: -0.1700

Data Index: 3819555 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1422. Min Act: -0.1700

Data Index: 5895967 (Open Web Text)

Max Activating Token Index: 523

Text #13

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1150. Min Act: -0.1700

Data Index: 2430697 (Open Web Text)

Max Activating Token Index: 907

Text #14

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1324. Min Act: -0.1700

Data Index: 5711401 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1121. Min Act: -0.1700

Data Index: 209153 (Open Web Text)

Max Activating Token Index: 266

Text #16

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1303. Min Act: -0.1700

Data Index: 467615 (Open Web Text)

Max Activating Token Index: 672

Text #17

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1273. Min Act: -0.1700

Data Index: 4038792 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1199. Min Act: -0.1700

Data Index: 5217788 (Open Web Text)

Max Activating Token Index: 353

Text #19

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1048. Min Act: -0.1700

Data Index: 7488869 (Open Web Text)

Max Activating Token Index: 216