Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 910 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1812. Min Range: -6.1812
Max Act: 6.1812. Min Act: -0.1700
Data Index: 499825 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1812. Min Range: -6.1812
Max Act: 6.0562. Min Act: -0.1700
Data Index: 4120186 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1812. Min Range: -6.1812
Max Act: 6.0250. Min Act: -0.1700
Data Index: 4636307 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1812. Min Range: -6.1812
Max Act: 6.0562. Min Act: -0.1700
Data Index: 8505677 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1812. Min Range: -6.1812
Max Act: 6.0250. Min Act: -0.1700
Data Index: 5544420 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.9937. Min Act: -0.1700
Data Index: 4824456 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.9937. Min Act: -0.1700
Data Index: 4593603 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.9937. Min Act: -0.1700
Data Index: 1334236 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1812. Min Range: -6.1812
Max Act: 6.0250. Min Act: -0.1700
Data Index: 6486564 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.9625. Min Act: -0.1700
Data Index: 8000879 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.9000. Min Act: -0.1700
Data Index: 610011 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.8687. Min Act: -0.1700
Data Index: 2674568 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.8687. Min Act: -0.1700
Data Index: 2326723 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.8687. Min Act: -0.1700
Data Index: 5544324 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.8687. Min Act: -0.1700
Data Index: 3426066 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.9000. Min Act: -0.1700
Data Index: 5544325 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.8375. Min Act: -0.1700
Data Index: 852838 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.8375. Min Act: -0.1700
Data Index: 966726 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.8375. Min Act: -0.1700
Data Index: 5764321 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1812. Min Range: -6.1812
Max Act: 5.8375. Min Act: -0.1700
Data Index: 5880588 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19