Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1610 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0265. Min Range: -7.0265
Max Act: 7.0265. Min Act: -0.1700
Data Index: 3650348 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.9015. Min Act: -0.1700
Data Index: 2112112 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.9015. Min Act: -0.1700
Data Index: 2680716 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.8703. Min Act: -0.1700
Data Index: 1590423 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.8390. Min Act: -0.1700
Data Index: 511777 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.7765. Min Act: -0.1700
Data Index: 3537742 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.7453. Min Act: -0.1700
Data Index: 3068136 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.7453. Min Act: -0.1700
Data Index: 954756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.7140. Min Act: -0.1700
Data Index: 3738818 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.6515. Min Act: -0.1700
Data Index: 5871664 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.5890. Min Act: -0.1700
Data Index: 1744814 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.6203. Min Act: -0.1700
Data Index: 6866674 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.5578. Min Act: -0.1700
Data Index: 3452899 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.5578. Min Act: -0.1700
Data Index: 2083557 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.5265. Min Act: -0.1700
Data Index: 5491781 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.5265. Min Act: -0.1700
Data Index: 4116104 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.4953. Min Act: -0.1700
Data Index: 8681769 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.4953. Min Act: -0.1700
Data Index: 5650033 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.5265. Min Act: -0.1700
Data Index: 6152031 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0265. Min Range: -7.0265
Max Act: 6.4953. Min Act: -0.1700
Data Index: 281013 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19