Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2067 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2006. Min Range: -8.2006
Max Act: 8.2006. Min Act: -0.1700
Data Index: 660069 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.5756. Min Act: -0.1700
Data Index: 2101953 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.5131. Min Act: -0.1700
Data Index: 2763571 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.3881. Min Act: -0.1700
Data Index: 115118 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.2943. Min Act: -0.1700
Data Index: 8009647 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.2006. Min Act: -0.1700
Data Index: 4447006 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.1693. Min Act: -0.1700
Data Index: 713144 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.1381. Min Act: -0.1700
Data Index: 3628858 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.1068. Min Act: -0.1700
Data Index: 8205201 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.1068. Min Act: -0.1700
Data Index: 8449393 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.0756. Min Act: -0.1700
Data Index: 7993462 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.0443. Min Act: -0.1700
Data Index: 7036664 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2006. Min Range: -8.2006
Max Act: 7.0131. Min Act: -0.1700
Data Index: 8280257 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2006. Min Range: -8.2006
Max Act: 6.9818. Min Act: -0.1700
Data Index: 1109160 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2006. Min Range: -8.2006
Max Act: 6.9818. Min Act: -0.1700
Data Index: 7939699 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2006. Min Range: -8.2006
Max Act: 6.9818. Min Act: -0.1700
Data Index: 4696636 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2006. Min Range: -8.2006
Max Act: 6.9193. Min Act: -0.1700
Data Index: 3694185 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2006. Min Range: -8.2006
Max Act: 6.9506. Min Act: -0.1700
Data Index: 3618851 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2006. Min Range: -8.2006
Max Act: 6.9506. Min Act: -0.1700
Data Index: 853079 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2006. Min Range: -8.2006
Max Act: 6.9193. Min Act: -0.1700
Data Index: 4303070 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19