Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0363. Min Range: -6.0363
Max Act: 6.0363. Min Act: -0.1700
Data Index: 7208969 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.9113. Min Act: -0.1700
Data Index: 6378739 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.7551. Min Act: -0.1700
Data Index: 1748442 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.7238. Min Act: -0.1700
Data Index: 5670043 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.6926. Min Act: -0.1700
Data Index: 4478970 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5988. Min Act: -0.1700
Data Index: 5356223 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1384770 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1352450 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1971727 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5676. Min Act: -0.1700
Data Index: 4104711 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5676. Min Act: -0.1700
Data Index: 4590255 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5363. Min Act: -0.1700
Data Index: 3098755 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5363. Min Act: -0.1700
Data Index: 660422 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5363. Min Act: -0.1700
Data Index: 2418132 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5363. Min Act: -0.1700
Data Index: 857964 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5363. Min Act: -0.1700
Data Index: 277104 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5051. Min Act: -0.1700
Data Index: 413663 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5051. Min Act: -0.1700
Data Index: 5185542 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5051. Min Act: -0.1700
Data Index: 932734 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0363. Min Range: -6.0363
Max Act: 5.5051. Min Act: -0.1700
Data Index: 1048750 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19