Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2154 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0519. Min Range: -6.0519
Max Act: 6.0519. Min Act: -0.1700
Data Index: 1475778 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.9582. Min Act: -0.1700
Data Index: 3878188 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.9269. Min Act: -0.1700
Data Index: 5608491 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.8644. Min Act: -0.1700
Data Index: 6751487 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.8644. Min Act: -0.1700
Data Index: 5001152 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.8644. Min Act: -0.1700
Data Index: 8409955 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.8019. Min Act: -0.1700
Data Index: 2520744 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.8019. Min Act: -0.1700
Data Index: 404168 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.8019. Min Act: -0.1700
Data Index: 7433812 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.7707. Min Act: -0.1700
Data Index: 7882388 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.7707. Min Act: -0.1700
Data Index: 3772614 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.7082. Min Act: -0.1700
Data Index: 4859734 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.6769. Min Act: -0.1700
Data Index: 3343341 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.6769. Min Act: -0.1700
Data Index: 1184471 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.6769. Min Act: -0.1700
Data Index: 2936581 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.6769. Min Act: -0.1700
Data Index: 2897744 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.6769. Min Act: -0.1700
Data Index: 5932616 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.6457. Min Act: -0.1700
Data Index: 472056 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.6457. Min Act: -0.1700
Data Index: 4577623 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0519. Min Range: -6.0519
Max Act: 5.6457. Min Act: -0.1700
Data Index: 5090896 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19