Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.6267. Min Act: -0.1700
Data Index: 8565377 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.6267. Min Act: -0.1700
Data Index: 7397542 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.5642. Min Act: -0.1700
Data Index: 8750307 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.5642. Min Act: -0.1700
Data Index: 8188345 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.5017. Min Act: -0.1700
Data Index: 6959227 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.3767. Min Act: -0.1700
Data Index: 1556860 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.3142. Min Act: -0.1700
Data Index: 2660083 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.3142. Min Act: -0.1700
Data Index: 2410842 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.3142. Min Act: -0.1700
Data Index: 6371831 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.2517. Min Act: -0.1700
Data Index: 4051182 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1892. Min Act: -0.1700
Data Index: 6693497 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.2517. Min Act: -0.1700
Data Index: 4635645 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1892. Min Act: -0.1700
Data Index: 1170957 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 4771752 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 7391323 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 4437849 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 1179916 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 5462727 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 592059 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6267. Min Range: -8.6267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 5771696 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19