Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1630. Min Act: -0.1700
Data Index: 161162 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1317. Min Act: -0.1700
Data Index: 2518276 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1317. Min Act: -0.1700
Data Index: 5639873 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1005. Min Act: -0.1700
Data Index: 2322882 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1317. Min Act: -0.1700
Data Index: 3649908 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1317. Min Act: -0.1700
Data Index: 7236021 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1317. Min Act: -0.1700
Data Index: 1727688 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1005. Min Act: -0.1700
Data Index: 6782941 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1005. Min Act: -0.1700
Data Index: 1204890 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1005. Min Act: -0.1700
Data Index: 1853738 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1005. Min Act: -0.1700
Data Index: 6846641 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0692. Min Act: -0.1700
Data Index: 1698522 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0692. Min Act: -0.1700
Data Index: 400927 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0380. Min Act: -0.1700
Data Index: 2665813 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0380. Min Act: -0.1700
Data Index: 562856 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0692. Min Act: -0.1700
Data Index: 3795351 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0067. Min Act: -0.1700
Data Index: 6403866 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0067. Min Act: -0.1700
Data Index: 2379176 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0067. Min Act: -0.1700
Data Index: 4319771 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0067. Min Act: -0.1700
Data Index: 4320062 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19