Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1055. Min Range: -6.1055
Max Act: 6.1055. Min Act: -0.1700
Data Index: 4055087 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1055. Min Range: -6.1055
Max Act: 6.1055. Min Act: -0.1700
Data Index: 2412013 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.9805. Min Act: -0.1700
Data Index: 2843389 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.9492. Min Act: -0.1700
Data Index: 5928594 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.9180. Min Act: -0.1700
Data Index: 6371310 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8867. Min Act: -0.1700
Data Index: 8637450 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8867. Min Act: -0.1700
Data Index: 5906749 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8867. Min Act: -0.1700
Data Index: 6449846 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8555. Min Act: -0.1700
Data Index: 6770773 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8555. Min Act: -0.1700
Data Index: 2488174 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8555. Min Act: -0.1700
Data Index: 7985516 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1700
Data Index: 2185871 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1696
Data Index: 2425755 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1700
Data Index: 1450656 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1700
Data Index: 475584 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1700
Data Index: 8117516 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1695
Data Index: 3629059 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1700
Data Index: 3645672 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1700
Data Index: 3712257 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1055. Min Range: -6.1055
Max Act: 5.8242. Min Act: -0.1700
Data Index: 4773845 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19