Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5960 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.9603. Min Act: -0.1700
Data Index: 2085726 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.9603. Min Act: -0.1700
Data Index: 5177611 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.8666. Min Act: -0.1700
Data Index: 2682538 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.8978. Min Act: -0.1700
Data Index: 7609498 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.8353. Min Act: -0.1700
Data Index: 3264249 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.8041. Min Act: -0.1700
Data Index: 8734539 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.8041. Min Act: -0.1700
Data Index: 8268756 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.8041. Min Act: -0.1700
Data Index: 7784305 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.7728. Min Act: -0.1700
Data Index: 7133812 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.7103. Min Act: -0.1700
Data Index: 7032941 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.7103. Min Act: -0.1700
Data Index: 1275623 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.6791. Min Act: -0.1700
Data Index: 3548620 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.6791. Min Act: -0.1700
Data Index: 7803781 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.6166. Min Act: -0.1700
Data Index: 5914806 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.6166. Min Act: -0.1700
Data Index: 278602 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.5853. Min Act: -0.1700
Data Index: 154299 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.5853. Min Act: -0.1700
Data Index: 8041198 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.5541. Min Act: -0.1700
Data Index: 4928835 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.5541. Min Act: -0.1700
Data Index: 733524 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9603. Min Range: -6.9603
Max Act: 6.5228. Min Act: -0.1700
Data Index: 6709473 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19