Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2049 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3814. Min Range: -4.3814
Max Act: 4.3814. Min Act: -0.1700
Data Index: 5397917 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3814. Min Range: -4.3814
Max Act: 4.2251. Min Act: -0.1700
Data Index: 8419494 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.9751. Min Act: -0.1700
Data Index: 5672338 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.9438. Min Act: -0.1700
Data Index: 5021355 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.9438. Min Act: -0.1700
Data Index: 3751539 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.9125. Min Act: -0.1700
Data Index: 3937981 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.9125. Min Act: -0.1700
Data Index: 4884377 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8813. Min Act: -0.1700
Data Index: 5036160 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8813. Min Act: -0.1700
Data Index: 5002569 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8813. Min Act: -0.1700
Data Index: 8343095 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8813. Min Act: -0.1700
Data Index: 3273043 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8500. Min Act: -0.1700
Data Index: 3647631 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8813. Min Act: -0.1700
Data Index: 6153884 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8187. Min Act: -0.1700
Data Index: 3168894 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8187. Min Act: -0.1700
Data Index: 1445322 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.8187. Min Act: -0.1700
Data Index: 6911779 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.7875. Min Act: -0.1700
Data Index: 6871105 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.7875. Min Act: -0.1700
Data Index: 6633844 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.7875. Min Act: -0.1700
Data Index: 744140 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3814. Min Range: -4.3814
Max Act: 3.7875. Min Act: -0.1700
Data Index: 788456 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19