Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1882 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5782. Min Range: -8.5782
Max Act: 8.5782. Min Act: -0.1700
Data Index: 7478563 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5782. Min Range: -8.5782
Max Act: 8.2032. Min Act: -0.1700
Data Index: 4947095 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5782. Min Range: -8.5782
Max Act: 8.1407. Min Act: -0.1700
Data Index: 3402013 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5782. Min Range: -8.5782
Max Act: 8.0157. Min Act: -0.1700
Data Index: 2655263 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5782. Min Range: -8.5782
Max Act: 8.0157. Min Act: -0.1700
Data Index: 4289412 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.9532. Min Act: -0.1700
Data Index: 3964 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.9532. Min Act: -0.1700
Data Index: 3225094 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.8907. Min Act: -0.1700
Data Index: 3031893 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.8907. Min Act: -0.1700
Data Index: 3916002 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.8907. Min Act: -0.1700
Data Index: 1754907 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.8282. Min Act: -0.1700
Data Index: 8623680 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.8282. Min Act: -0.1700
Data Index: 3771991 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.8282. Min Act: -0.1700
Data Index: 1993067 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.7657. Min Act: -0.1700
Data Index: 7624136 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.7657. Min Act: -0.1700
Data Index: 2359580 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.7657. Min Act: -0.1700
Data Index: 7990219 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.7657. Min Act: -0.1700
Data Index: 1361234 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.7657. Min Act: -0.1700
Data Index: 163520 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.7657. Min Act: -0.1700
Data Index: 8114903 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5782. Min Range: -8.5782
Max Act: 7.7032. Min Act: -0.1700
Data Index: 215879 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19