Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2582 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.9482. Min Act: -0.1700
Data Index: 1760533 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.9794. Min Act: -0.1700
Data Index: 6640547 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.8857. Min Act: -0.1700
Data Index: 7784472 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.7607. Min Act: -0.1700
Data Index: 4654668 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.7919. Min Act: -0.1700
Data Index: 1846997 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.7607. Min Act: -0.1700
Data Index: 3337774 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.7607. Min Act: -0.1700
Data Index: 3510052 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.7294. Min Act: -0.1700
Data Index: 2849526 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6669. Min Act: -0.1700
Data Index: 5279251 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6982. Min Act: -0.1700
Data Index: 1798931 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6357. Min Act: -0.1700
Data Index: 236964 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6357. Min Act: -0.1700
Data Index: 2468884 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6357. Min Act: -0.1700
Data Index: 6296844 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6357. Min Act: -0.1700
Data Index: 3337775 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6044. Min Act: -0.1700
Data Index: 136667 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6044. Min Act: -0.1700
Data Index: 8225870 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6044. Min Act: -0.1700
Data Index: 4057173 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.5732. Min Act: -0.1700
Data Index: 7339201 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6044. Min Act: -0.1700
Data Index: 6999030 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9794. Min Range: -6.9794
Max Act: 6.6044. Min Act: -0.1700
Data Index: 1776202 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19