Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2079 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2017. Min Range: -7.2017
Max Act: 7.2017. Min Act: -0.1700
Data Index: 1608587 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2017. Min Range: -7.2017
Max Act: 7.1705. Min Act: -0.1700
Data Index: 5273317 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2017. Min Range: -7.2017
Max Act: 7.2017. Min Act: -0.1700
Data Index: 531955 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2017. Min Range: -7.2017
Max Act: 7.0767. Min Act: -0.1700
Data Index: 5949426 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2017. Min Range: -7.2017
Max Act: 7.0142. Min Act: -0.1700
Data Index: 8102271 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2017. Min Range: -7.2017
Max Act: 7.0455. Min Act: -0.1700
Data Index: 6862002 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2017. Min Range: -7.2017
Max Act: 7.0142. Min Act: -0.1700
Data Index: 1053571 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.9517. Min Act: -0.1700
Data Index: 2446044 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.9517. Min Act: -0.1700
Data Index: 1034251 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.9517. Min Act: -0.1700
Data Index: 5781109 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.9517. Min Act: -0.1700
Data Index: 2057094 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.9517. Min Act: -0.1700
Data Index: 7615868 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.8892. Min Act: -0.1700
Data Index: 4277936 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.8892. Min Act: -0.1700
Data Index: 8663041 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.8892. Min Act: -0.1700
Data Index: 6395888 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.8580. Min Act: -0.1700
Data Index: 138815 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.8580. Min Act: -0.1700
Data Index: 6091554 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.8892. Min Act: -0.1700
Data Index: 8633137 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.8267. Min Act: -0.1700
Data Index: 4659722 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2017. Min Range: -7.2017
Max Act: 6.8267. Min Act: -0.1700
Data Index: 1558466 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19