Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2788 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.6812. Min Act: -0.1700
Data Index: 6802915 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.5562. Min Act: -0.1700
Data Index: 206267 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.3687. Min Act: -0.1700
Data Index: 4470570 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.3687. Min Act: -0.1700
Data Index: 3752370 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.2437. Min Act: -0.1700
Data Index: 3567893 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.2437. Min Act: -0.1700
Data Index: 3796315 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.2437. Min Act: -0.1700
Data Index: 4009223 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.1812. Min Act: -0.1700
Data Index: 7066680 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.1187. Min Act: -0.1700
Data Index: 879313 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.1187. Min Act: -0.1700
Data Index: 4362002 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.1187. Min Act: -0.1700
Data Index: 1324825 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.1187. Min Act: -0.1700
Data Index: 3061880 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.0562. Min Act: -0.1700
Data Index: 7411590 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.1187. Min Act: -0.1700
Data Index: 6659954 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.0562. Min Act: -0.1700
Data Index: 6943353 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.1187. Min Act: -0.1700
Data Index: 6496385 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.0562. Min Act: -0.1700
Data Index: 4358989 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6812. Min Range: -8.6812
Max Act: 7.9937. Min Act: -0.1700
Data Index: 2325462 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6812. Min Range: -8.6812
Max Act: 7.9937. Min Act: -0.1700
Data Index: 6445897 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6812. Min Range: -8.6812
Max Act: 8.0562. Min Act: -0.1700
Data Index: 6783716 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19