Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3985 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8211. Min Range: -7.8211
Max Act: 7.8211. Min Act: -0.1700
Data Index: 3420409 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8211. Min Range: -7.8211
Max Act: 7.3211. Min Act: -0.1700
Data Index: 3420413 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8211. Min Range: -7.8211
Max Act: 7.1024. Min Act: -0.1700
Data Index: 26592 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.9461. Min Act: -0.1700
Data Index: 3832594 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.9461. Min Act: -0.1700
Data Index: 2030079 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.9149. Min Act: -0.1700
Data Index: 1664511 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.8524. Min Act: -0.1698
Data Index: 8115851 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.8211. Min Act: -0.1700
Data Index: 8495907 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.8524. Min Act: -0.1698
Data Index: 6100789 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.8211. Min Act: -0.1700
Data Index: 7003348 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.8211. Min Act: -0.1700
Data Index: 2236092 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.7586. Min Act: -0.1700
Data Index: 2290768 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.6961. Min Act: -0.1700
Data Index: 4650791 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.6961. Min Act: -0.1700
Data Index: 2924094 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.6649. Min Act: -0.1698
Data Index: 112861 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.6649. Min Act: -0.1700
Data Index: 2802253 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.6024. Min Act: -0.1700
Data Index: 5286978 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.6024. Min Act: -0.1700
Data Index: 2818578 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.5711. Min Act: -0.1700
Data Index: 3876608 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8211. Min Range: -7.8211
Max Act: 6.6024. Min Act: -0.1700
Data Index: 3892479 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19