Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1538 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1643. Min Range: -7.1643
Max Act: 7.1643. Min Act: -0.1700
Data Index: 69805 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1643. Min Range: -7.1643
Max Act: 7.0080. Min Act: -0.1700
Data Index: 3878559 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.8205. Min Act: -0.1700
Data Index: 7302586 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.8205. Min Act: -0.1700
Data Index: 5740094 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.7893. Min Act: -0.1700
Data Index: 1100282 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.7580. Min Act: -0.1700
Data Index: 5485110 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.7580. Min Act: -0.1700
Data Index: 112990 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.6955. Min Act: -0.1700
Data Index: 5345137 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.6955. Min Act: -0.1700
Data Index: 558542 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1614949 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1469610 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.6643. Min Act: -0.1700
Data Index: 1881226 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.6643. Min Act: -0.1700
Data Index: 5449918 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.6643. Min Act: -0.1700
Data Index: 2542141 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.6643. Min Act: -0.1700
Data Index: 4179047 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.6330. Min Act: -0.1700
Data Index: 3650889 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.6643. Min Act: -0.1700
Data Index: 4478566 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.5705. Min Act: -0.1700
Data Index: 4977251 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.5705. Min Act: -0.1700
Data Index: 7890635 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1643. Min Range: -7.1643
Max Act: 6.5393. Min Act: -0.1700
Data Index: 7965725 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19