Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3014 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1267. Min Range: -12.1267
Max Act: 12.1267. Min Act: -0.1700
Data Index: 3450285 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1267. Min Range: -12.1267
Max Act: 12.0017. Min Act: -0.1700
Data Index: 6000735 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1267. Min Range: -12.1267
Max Act: 12.0017. Min Act: -0.1700
Data Index: 5148468 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.9392. Min Act: -0.1700
Data Index: 5498317 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.9392. Min Act: -0.1700
Data Index: 3120757 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.8767. Min Act: -0.1700
Data Index: 3996769 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.8767. Min Act: -0.1700
Data Index: 8804608 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.8767. Min Act: -0.1700
Data Index: 2174377 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.8142. Min Act: -0.1700
Data Index: 810998 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.8142. Min Act: -0.1700
Data Index: 1069018 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.6892. Min Act: -0.1700
Data Index: 6126565 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.7517. Min Act: -0.1700
Data Index: 8329902 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.6892. Min Act: -0.1700
Data Index: 7205715 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.5642. Min Act: -0.1700
Data Index: 6956569 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.6267. Min Act: -0.1700
Data Index: 2855488 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.5642. Min Act: -0.1700
Data Index: 4947388 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.5642. Min Act: -0.1700
Data Index: 6282922 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.5017. Min Act: -0.1700
Data Index: 5875299 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.4392. Min Act: -0.1700
Data Index: 774563 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1267. Min Range: -12.1267
Max Act: 11.4392. Min Act: -0.1700
Data Index: 2527049 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19