Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5571 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1955. Min Range: -4.1955
Max Act: 4.1955. Min Act: -0.1700
Data Index: 4949888 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1955. Min Range: -4.1955
Max Act: 4.1955. Min Act: -0.1700
Data Index: 7595438 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1955. Min Range: -4.1955
Max Act: 4.1017. Min Act: -0.1700
Data Index: 1051068 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1955. Min Range: -4.1955
Max Act: 4.0704. Min Act: -0.1700
Data Index: 4080 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1955. Min Range: -4.1955
Max Act: 4.0392. Min Act: -0.1700
Data Index: 2375217 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1955. Min Range: -4.1955
Max Act: 4.0392. Min Act: -0.1700
Data Index: 3030338 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1955. Min Range: -4.1955
Max Act: 4.0079. Min Act: -0.1700
Data Index: 4212360 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9767. Min Act: -0.1700
Data Index: 1825603 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9767. Min Act: -0.1700
Data Index: 7768900 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1955. Min Range: -4.1955
Max Act: 4.0079. Min Act: -0.1700
Data Index: 60341 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9767. Min Act: -0.1700
Data Index: 1025488 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9767. Min Act: -0.1700
Data Index: 4555387 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9454. Min Act: -0.1700
Data Index: 2491891 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9454. Min Act: -0.1700
Data Index: 4322647 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9454. Min Act: -0.1700
Data Index: 4298662 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9454. Min Act: -0.1700
Data Index: 6157741 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.8829. Min Act: -0.1700
Data Index: 7983272 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9141. Min Act: -0.1700
Data Index: 8424492 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.9141. Min Act: -0.1700
Data Index: 1713285 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1955. Min Range: -4.1955
Max Act: 3.8829. Min Act: -0.1700
Data Index: 3687531 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19