Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3240 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.5074. Min Act: -0.1700
Data Index: 5876942 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.5074. Min Act: -0.1700
Data Index: 405299 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.4449. Min Act: -0.1700
Data Index: 7157254 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.3824. Min Act: -0.1700
Data Index: 7529382 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.3824. Min Act: -0.1700
Data Index: 3805614 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.3824. Min Act: -0.1700
Data Index: 5994274 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.3824. Min Act: -0.1700
Data Index: 6938751 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.3824. Min Act: -0.1700
Data Index: 4494653 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.2887. Min Act: -0.1700
Data Index: 1118143 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.2887. Min Act: -0.1700
Data Index: 322894 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.2574. Min Act: -0.1700
Data Index: 3805611 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.2262. Min Act: -0.1700
Data Index: 6009452 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.2262. Min Act: -0.1700
Data Index: 3805598 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.2262. Min Act: -0.1700
Data Index: 694797 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.2262. Min Act: -0.1700
Data Index: 694800 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.1949. Min Act: -0.1700
Data Index: 5117665 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.1949. Min Act: -0.1700
Data Index: 694790 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.1637. Min Act: -0.1700
Data Index: 2489174 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.1637. Min Act: -0.1700
Data Index: 2557438 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5074. Min Range: -8.5074
Max Act: 8.1324. Min Act: -0.1700
Data Index: 3165492 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19