Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6186 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0752. Min Range: -12.0752
Max Act: 12.0752. Min Act: -0.1700
Data Index: 4623636 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0752. Min Range: -12.0752
Max Act: 11.7002. Min Act: -0.1700
Data Index: 4859854 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0752. Min Range: -12.0752
Max Act: 11.2002. Min Act: -0.1700
Data Index: 1532546 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0752. Min Range: -12.0752
Max Act: 11.0752. Min Act: -0.1700
Data Index: 2040951 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0752. Min Range: -12.0752
Max Act: 11.0752. Min Act: -0.1699
Data Index: 402918 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0752. Min Range: -12.0752
Max Act: 11.0127. Min Act: -0.1700
Data Index: 7063660 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.9502. Min Act: -0.1700
Data Index: 5171558 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.9502. Min Act: -0.1700
Data Index: 5946707 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.8877. Min Act: -0.1700
Data Index: 695955 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.8877. Min Act: -0.1700
Data Index: 294963 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.8877. Min Act: -0.1700
Data Index: 3063739 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.8252. Min Act: -0.1700
Data Index: 7014284 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.7627. Min Act: -0.1700
Data Index: 1010049 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.7627. Min Act: -0.1700
Data Index: 8793945 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.7627. Min Act: -0.1700
Data Index: 104833 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.7002. Min Act: -0.1700
Data Index: 3274389 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.7002. Min Act: -0.1700
Data Index: 4669620 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.6377. Min Act: -0.1700
Data Index: 729725 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.7002. Min Act: -0.1700
Data Index: 401785 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0752. Min Range: -12.0752
Max Act: 10.6377. Min Act: -0.1700
Data Index: 666754 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19