Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3801 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1668. Min Range: -6.1668
Max Act: 6.1668. Min Act: -0.1700
Data Index: 5810773 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.7918. Min Act: -0.1700
Data Index: 1054996 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.7606. Min Act: -0.1700
Data Index: 407006 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.6981. Min Act: -0.1700
Data Index: 6593320 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.6668. Min Act: -0.1700
Data Index: 7166593 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.6668. Min Act: -0.1700
Data Index: 5769389 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.6043. Min Act: -0.1700
Data Index: 6704031 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.5731. Min Act: -0.1700
Data Index: 180759 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.5731. Min Act: -0.1700
Data Index: 7252441 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.4793. Min Act: -0.1700
Data Index: 8319629 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.4481. Min Act: -0.1700
Data Index: 255201 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.4793. Min Act: -0.1700
Data Index: 6786078 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.4481. Min Act: -0.1700
Data Index: 3171318 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.4481. Min Act: -0.1700
Data Index: 8454374 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.4481. Min Act: -0.1700
Data Index: 5210611 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.4481. Min Act: -0.1700
Data Index: 7837515 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.3856. Min Act: -0.1700
Data Index: 5116610 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.3856. Min Act: -0.1700
Data Index: 474403 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.3543. Min Act: -0.1700
Data Index: 5968345 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1668. Min Range: -6.1668
Max Act: 5.3543. Min Act: -0.1700
Data Index: 6260365 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19