Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.6887. Min Act: -0.1700
Data Index: 7499204 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.6262. Min Act: -0.1700
Data Index: 5553550 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.6262. Min Act: -0.1700
Data Index: 6751393 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.5950. Min Act: -0.1700
Data Index: 2349507 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.5637. Min Act: -0.1700
Data Index: 7846372 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.5637. Min Act: -0.1700
Data Index: 1407293 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4700. Min Act: -0.1700
Data Index: 6544884 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4700. Min Act: -0.1700
Data Index: 1917863 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4700. Min Act: -0.1700
Data Index: 6646626 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4387. Min Act: -0.1700
Data Index: 4087025 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4387. Min Act: -0.1700
Data Index: 8562348 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4387. Min Act: -0.1700
Data Index: 8776547 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4387. Min Act: -0.1700
Data Index: 2109890 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4387. Min Act: -0.1700
Data Index: 3155949 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4387. Min Act: -0.1700
Data Index: 8257895 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4075. Min Act: -0.1700
Data Index: 1245603 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4387. Min Act: -0.1700
Data Index: 7029468 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4075. Min Act: -0.1700
Data Index: 2445898 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4075. Min Act: -0.1700
Data Index: 128384 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6887. Min Range: -4.6887
Max Act: 4.4075. Min Act: -0.1700
Data Index: 570668 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19