Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1618 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.7718. Min Act: -0.1700
Data Index: 4019183 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.2093. Min Act: -0.1700
Data Index: 5492451 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.1155. Min Act: -0.1700
Data Index: 6429768 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.1155. Min Act: -0.1700
Data Index: 7070474 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.1155. Min Act: -0.1700
Data Index: 7303298 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 781100 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 2403265 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 6101916 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 5881720 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 2403261 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 5881706 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 8560819 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 7736340 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 4337226 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 386303 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 6882582 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0843. Min Act: -0.1700
Data Index: 1300757 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0530. Min Act: -0.1700
Data Index: 4586514 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0530. Min Act: -0.1700
Data Index: 6234732 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7718. Min Range: -5.7718
Max Act: 5.0530. Min Act: -0.1700
Data Index: 377676 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19