Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4747 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1814. Min Act: -0.1700
Data Index: 4456064 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1814. Min Act: -0.1700
Data Index: 2932571 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1814. Min Act: -0.1700
Data Index: 1567750 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1814. Min Act: -0.1700
Data Index: 4435324 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0876. Min Act: -0.1700
Data Index: 446600 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0876. Min Act: -0.1700
Data Index: 8284778 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0564. Min Act: -0.1700
Data Index: 523454 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0251. Min Act: -0.1700
Data Index: 7253668 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0251. Min Act: -0.1700
Data Index: 7197949 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9939. Min Act: -0.1700
Data Index: 1581811 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9626. Min Act: -0.1700
Data Index: 6093651 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9939. Min Act: -0.1700
Data Index: 7204910 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9939. Min Act: -0.1700
Data Index: 7253669 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9939. Min Act: -0.1700
Data Index: 7205136 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9939. Min Act: -0.1700
Data Index: 120006 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9626. Min Act: -0.1700
Data Index: 5934526 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9626. Min Act: -0.1700
Data Index: 1999312 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9626. Min Act: -0.1700
Data Index: 4147126 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9626. Min Act: -0.1700
Data Index: 4265488 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1814. Min Range: -5.1814
Max Act: 4.9314. Min Act: -0.1700
Data Index: 8905 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19