Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5687. Min Act: -0.1700
Data Index: 5009891 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5687. Min Act: -0.1700
Data Index: 7687113 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5375. Min Act: -0.1700
Data Index: 5553977 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5062. Min Act: -0.1700
Data Index: 4347138 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5062. Min Act: -0.1700
Data Index: 2705211 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5062. Min Act: -0.1700
Data Index: 7354099 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.5062. Min Act: -0.1700
Data Index: 5000145 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.4437. Min Act: -0.1700
Data Index: 5539548 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.4125. Min Act: -0.1700
Data Index: 7586593 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.4125. Min Act: -0.1700
Data Index: 2647945 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.4125. Min Act: -0.1700
Data Index: 3199968 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3812. Min Act: -0.1700
Data Index: 6188014 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3812. Min Act: -0.1700
Data Index: 1184201 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3812. Min Act: -0.1700
Data Index: 7853243 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 3718513 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 2355493 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 1188449 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 7723749 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3500. Min Act: -0.1700
Data Index: 6287910 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5687. Min Range: -4.5687
Max Act: 4.3187. Min Act: -0.1700
Data Index: 5442360 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19