Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5585 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2827. Min Range: -4.2827
Max Act: 4.2827. Min Act: -0.1700
Data Index: 8749805 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2827. Min Range: -4.2827
Max Act: 4.2827. Min Act: -0.1700
Data Index: 7303489 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2827. Min Range: -4.2827
Max Act: 4.2515. Min Act: -0.1700
Data Index: 5534729 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2827. Min Range: -4.2827
Max Act: 4.2515. Min Act: -0.1700
Data Index: 6180364 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2827. Min Range: -4.2827
Max Act: 4.1265. Min Act: -0.1700
Data Index: 8220320 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2827. Min Range: -4.2827
Max Act: 4.0014. Min Act: -0.1700
Data Index: 5812827 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2827. Min Range: -4.2827
Max Act: 4.0014. Min Act: -0.1700
Data Index: 6457847 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.9702. Min Act: -0.1700
Data Index: 5566579 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.9702. Min Act: -0.1700
Data Index: 7547525 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2827. Min Range: -4.2827
Max Act: 4.0014. Min Act: -0.1700
Data Index: 8052955 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.9389. Min Act: -0.1700
Data Index: 8223472 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.9389. Min Act: -0.1700
Data Index: 2006953 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.9389. Min Act: -0.1700
Data Index: 6267003 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.8764. Min Act: -0.1700
Data Index: 8133181 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.8764. Min Act: -0.1700
Data Index: 4096913 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.8764. Min Act: -0.1700
Data Index: 4917045 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.8764. Min Act: -0.1700
Data Index: 7480100 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.8451. Min Act: -0.1700
Data Index: 3605044 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.8764. Min Act: -0.1700
Data Index: 4597158 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2827. Min Range: -4.2827
Max Act: 3.8295. Min Act: -0.1700
Data Index: 4278902 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19