Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2312. Min Range: -7.2312
Max Act: 7.2312. Min Act: -0.1700
Data Index: 5115562 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.8562. Min Act: -0.1700
Data Index: 3463053 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.8562. Min Act: -0.1700
Data Index: 8410439 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.8249. Min Act: -0.1700
Data Index: 4054649 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6687. Min Act: -0.1700
Data Index: 5281002 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6687. Min Act: -0.1700
Data Index: 5691299 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6062. Min Act: -0.1700
Data Index: 2959456 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6062. Min Act: -0.1700
Data Index: 7156674 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6062. Min Act: -0.1700
Data Index: 7489067 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.4812. Min Act: -0.1700
Data Index: 6316788 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.5124. Min Act: -0.1700
Data Index: 5800384 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.4812. Min Act: -0.1700
Data Index: 5349149 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.4812. Min Act: -0.1700
Data Index: 1876417 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.4187. Min Act: -0.1700
Data Index: 1531456 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.4187. Min Act: -0.1700
Data Index: 7372932 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.3874. Min Act: -0.1700
Data Index: 6635845 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.3874. Min Act: -0.1700
Data Index: 1639366 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.3562. Min Act: -0.1700
Data Index: 5298481 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.3562. Min Act: -0.1700
Data Index: 5364529 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.3562. Min Act: -0.1700
Data Index: 782924 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19