Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4143 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5845. Min Range: -9.5845
Max Act: 9.5845. Min Act: -0.1700
Data Index: 4453549 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5845. Min Range: -9.5845
Max Act: 9.2095. Min Act: -0.1700
Data Index: 3150391 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5845. Min Range: -9.5845
Max Act: 9.0845. Min Act: -0.1700
Data Index: 8178749 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5845. Min Range: -9.5845
Max Act: 9.0845. Min Act: -0.1700
Data Index: 6735015 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.9595. Min Act: -0.1700
Data Index: 8556112 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5845. Min Range: -9.5845
Max Act: 9.0220. Min Act: -0.1700
Data Index: 2573724 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5845. Min Range: -9.5845
Max Act: 9.0220. Min Act: -0.1700
Data Index: 2214775 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.9595. Min Act: -0.1700
Data Index: 1160899 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.9595. Min Act: -0.1700
Data Index: 1442108 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.8970. Min Act: -0.1700
Data Index: 7811302 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.8345. Min Act: -0.1700
Data Index: 2393079 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.8345. Min Act: -0.1700
Data Index: 1787928 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.7095. Min Act: -0.1700
Data Index: 4496184 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.8345. Min Act: -0.1700
Data Index: 5860268 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.7720. Min Act: -0.1700
Data Index: 5487589 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.7720. Min Act: -0.1700
Data Index: 207698 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.7720. Min Act: -0.1700
Data Index: 285645 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.7095. Min Act: -0.1700
Data Index: 3920823 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.6470. Min Act: -0.1700
Data Index: 6615801 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5845. Min Range: -9.5845
Max Act: 8.7720. Min Act: -0.1700
Data Index: 5540690 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19