Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4786. Min Range: -5.4786
Max Act: 5.4786. Min Act: -0.1700
Data Index: 7345183 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4786. Min Range: -5.4786
Max Act: 5.1348. Min Act: -0.1700
Data Index: 7848205 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4786. Min Range: -5.4786
Max Act: 5.1036. Min Act: -0.1700
Data Index: 4747031 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4786. Min Range: -5.4786
Max Act: 5.0723. Min Act: -0.1700
Data Index: 1171591 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4786. Min Range: -5.4786
Max Act: 5.0098. Min Act: -0.1700
Data Index: 2995788 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4786. Min Range: -5.4786
Max Act: 5.0098. Min Act: -0.1700
Data Index: 336415 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4786. Min Range: -5.4786
Max Act: 5.0098. Min Act: -0.1700
Data Index: 2003193 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 288412 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 1739746 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 4266975 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 3319799 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9786. Min Act: -0.1700
Data Index: 3145367 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9473. Min Act: -0.1700
Data Index: 4583884 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9473. Min Act: -0.1700
Data Index: 1119229 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9473. Min Act: -0.1700
Data Index: 274464 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9473. Min Act: -0.1700
Data Index: 6135578 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9161. Min Act: -0.1700
Data Index: 5060824 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9161. Min Act: -0.1700
Data Index: 3869520 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9161. Min Act: -0.1700
Data Index: 6972770 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4786. Min Range: -5.4786
Max Act: 4.9473. Min Act: -0.1700
Data Index: 4201042 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19