Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5517 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.6789. Min Act: -0.1700
Data Index: 641395 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.3039. Min Act: -0.1700
Data Index: 4830655 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.3352. Min Act: -0.1700
Data Index: 5363579 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.2102. Min Act: -0.1700
Data Index: 8403117 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.2102. Min Act: -0.1700
Data Index: 1391489 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.1477. Min Act: -0.1700
Data Index: 5480245 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.1789. Min Act: -0.1700
Data Index: 5056973 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.1477. Min Act: -0.1700
Data Index: 4307206 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.1164. Min Act: -0.1700
Data Index: 2665168 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.1164. Min Act: -0.1700
Data Index: 6920380 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.1164. Min Act: -0.1700
Data Index: 4084271 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0852. Min Act: -0.1700
Data Index: 8482483 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0852. Min Act: -0.1700
Data Index: 7916062 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0852. Min Act: -0.1700
Data Index: 7232542 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0852. Min Act: -0.1700
Data Index: 4295851 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0227. Min Act: -0.1700
Data Index: 1982906 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0227. Min Act: -0.1700
Data Index: 53552 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0227. Min Act: -0.1700
Data Index: 4284559 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0227. Min Act: -0.1700
Data Index: 5093267 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6789. Min Range: -6.6789
Max Act: 6.0539. Min Act: -0.1700
Data Index: 6848300 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19