Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3083. Min Range: -11.3083
Max Act: 11.3083. Min Act: -0.1700
Data Index: 4295377 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.5583. Min Act: -0.1700
Data Index: 2504483 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.4958. Min Act: -0.1700
Data Index: 8145836 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.3708. Min Act: -0.1700
Data Index: 1576093 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.3083. Min Act: -0.1700
Data Index: 7846564 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.3083. Min Act: -0.1700
Data Index: 1291912 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.3083. Min Act: -0.1700
Data Index: 2037499 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.2458. Min Act: -0.1700
Data Index: 5236953 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.2458. Min Act: -0.1700
Data Index: 4916744 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.2458. Min Act: -0.1700
Data Index: 2820038 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.2458. Min Act: -0.1700
Data Index: 2421760 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1833. Min Act: -0.1700
Data Index: 8430074 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1833. Min Act: -0.1700
Data Index: 545590 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1833. Min Act: -0.1700
Data Index: 6261029 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1833. Min Act: -0.1700
Data Index: 1432658 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1208. Min Act: -0.1700
Data Index: 7673813 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1208. Min Act: -0.1700
Data Index: 5702537 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1208. Min Act: -0.1700
Data Index: 5321124 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1208. Min Act: -0.1700
Data Index: 4430478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3083. Min Range: -11.3083
Max Act: 10.1208. Min Act: -0.1700
Data Index: 1603012 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19