Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0063. Min Range: -7.0063
Max Act: 7.0063. Min Act: -0.1700
Data Index: 74334 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.9438. Min Act: -0.1700
Data Index: 4404730 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.8188. Min Act: -0.1700
Data Index: 3863492 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.7563. Min Act: -0.1700
Data Index: 3698905 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.6000. Min Act: -0.1700
Data Index: 1491489 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.5063. Min Act: -0.1700
Data Index: 6744981 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.5375. Min Act: -0.1700
Data Index: 1050128 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.4438. Min Act: -0.1700
Data Index: 2277612 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.4750. Min Act: -0.1700
Data Index: 769203 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.4438. Min Act: -0.1700
Data Index: 7841058 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.4438. Min Act: -0.1700
Data Index: 6758737 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.4125. Min Act: -0.1700
Data Index: 7983690 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.3813. Min Act: -0.1700
Data Index: 3456899 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.3813. Min Act: -0.1700
Data Index: 2761469 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.3813. Min Act: -0.1700
Data Index: 3421860 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 2226192 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.3500. Min Act: -0.1700
Data Index: 3202536 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.2563. Min Act: -0.1700
Data Index: 2259281 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.2563. Min Act: -0.1700
Data Index: 2961280 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0063. Min Range: -7.0063
Max Act: 6.2250. Min Act: -0.1700
Data Index: 7028872 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19