Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5781 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.6492. Min Act: -0.1700
Data Index: 2044638 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.6492. Min Act: -0.1700
Data Index: 3177079 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.6492. Min Act: -0.1700
Data Index: 5625821 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.6180. Min Act: -0.1700
Data Index: 1479579 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.6492. Min Act: -0.1700
Data Index: 2492344 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.6180. Min Act: -0.1700
Data Index: 1738818 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.5867. Min Act: -0.1700
Data Index: 2372927 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.5242. Min Act: -0.1700
Data Index: 8341545 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.5242. Min Act: -0.1700
Data Index: 4960266 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.5242. Min Act: -0.1700
Data Index: 4516287 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.5242. Min Act: -0.1700
Data Index: 4532475 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.5242. Min Act: -0.1700
Data Index: 6451815 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4617. Min Act: -0.1700
Data Index: 7215758 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4930. Min Act: -0.1700
Data Index: 2654648 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4930. Min Act: -0.1700
Data Index: 6696006 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4930. Min Act: -0.1700
Data Index: 8224497 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4930. Min Act: -0.1700
Data Index: 959632 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4617. Min Act: -0.1700
Data Index: 8041214 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4617. Min Act: -0.1700
Data Index: 2372924 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4930. Min Act: -0.1700
Data Index: 782717 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19