Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.8156. Min Act: -0.1700
Data Index: 116540 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.7531. Min Act: -0.1700
Data Index: 659526 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.7531. Min Act: -0.1700
Data Index: 902620 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.7531. Min Act: -0.1700
Data Index: 8459068 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6906. Min Act: -0.1700
Data Index: 3631994 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6906. Min Act: -0.1700
Data Index: 5265937 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6906. Min Act: -0.1700
Data Index: 6886899 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6906. Min Act: -0.1700
Data Index: 4580839 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6906. Min Act: -0.1700
Data Index: 7461891 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6906. Min Act: -0.1700
Data Index: 1384856 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6906. Min Act: -0.1700
Data Index: 889977 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6281. Min Act: -0.1700
Data Index: 4022805 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6281. Min Act: -0.1700
Data Index: 2057159 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6281. Min Act: -0.1700
Data Index: 8729007 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6281. Min Act: -0.1700
Data Index: 3628718 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6281. Min Act: -0.1700
Data Index: 7106004 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6281. Min Act: -0.1700
Data Index: 6582666 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6281. Min Act: -0.1700
Data Index: 6276496 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.6281. Min Act: -0.1700
Data Index: 5885653 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8156. Min Range: -6.8156
Max Act: 6.5969. Min Act: -0.1700
Data Index: 800621 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19