Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.9878. Min Act: -0.1700
Data Index: 1091076 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.9720. Min Act: -0.1700
Data Index: 1729860 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.9245. Min Act: -0.1700
Data Index: 2007545 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.9403. Min Act: -0.1700
Data Index: 6348519 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.9245. Min Act: -0.1700
Data Index: 5478588 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.9245. Min Act: -0.1700
Data Index: 1535683 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.9245. Min Act: -0.1700
Data Index: 944676 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8928. Min Act: -0.1700
Data Index: 1721798 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8928. Min Act: -0.1700
Data Index: 646436 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8769. Min Act: -0.1700
Data Index: 5346990 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8610. Min Act: -0.1700
Data Index: 6765746 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8769. Min Act: -0.1700
Data Index: 6216291 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8610. Min Act: -0.1700
Data Index: 5902412 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8452. Min Act: -0.1700
Data Index: 8312980 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8452. Min Act: -0.1700
Data Index: 221583 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8293. Min Act: -0.1700
Data Index: 3179481 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8133. Min Act: -0.1700
Data Index: 6633867 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8133. Min Act: -0.1700
Data Index: 5028055 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8293. Min Act: -0.1700
Data Index: 7269005 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7974. Min Act: -0.1700
Data Index: 1342175 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19