Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2092 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0032. Min Range: -6.0032
Max Act: 6.0032. Min Act: -0.1700
Data Index: 7297403 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7844. Min Act: -0.1700
Data Index: 8797892 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7844. Min Act: -0.1700
Data Index: 4857132 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7532. Min Act: -0.1700
Data Index: 2327855 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7219. Min Act: -0.1700
Data Index: 6478734 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7219. Min Act: -0.1700
Data Index: 1948246 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6907. Min Act: -0.1700
Data Index: 7895776 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6907. Min Act: -0.1700
Data Index: 3871260 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6594. Min Act: -0.1700
Data Index: 142747 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6594. Min Act: -0.1700
Data Index: 1510311 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6594. Min Act: -0.1700
Data Index: 5192587 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6282. Min Act: -0.1700
Data Index: 6300801 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6282. Min Act: -0.1700
Data Index: 3287344 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6594. Min Act: -0.1700
Data Index: 925490 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6282. Min Act: -0.1700
Data Index: 1698620 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5969. Min Act: -0.1700
Data Index: 2272445 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5969. Min Act: -0.1700
Data Index: 6648461 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5657. Min Act: -0.1700
Data Index: 3980056 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5657. Min Act: -0.1700
Data Index: 5371649 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5657. Min Act: -0.1700
Data Index: 3207626 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19