Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4208 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.9718. Min Act: -0.1700
Data Index: 6168805 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.7218. Min Act: -0.1700
Data Index: 6204835 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.7218. Min Act: -0.1700
Data Index: 8445545 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.7218. Min Act: -0.1700
Data Index: 7672529 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.7218. Min Act: -0.1700
Data Index: 5642484 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.6593. Min Act: -0.1700
Data Index: 776780 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.5968. Min Act: -0.1700
Data Index: 3469283 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.5968. Min Act: -0.1700
Data Index: 6180088 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.5655. Min Act: -0.1700
Data Index: 2943882 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.5655. Min Act: -0.1700
Data Index: 4175437 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.5030. Min Act: -0.1700
Data Index: 3797046 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.5343. Min Act: -0.1700
Data Index: 4879370 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.5030. Min Act: -0.1700
Data Index: 1384159 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.5030. Min Act: -0.1700
Data Index: 4561791 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.4718. Min Act: -0.1700
Data Index: 4695286 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.4718. Min Act: -0.1700
Data Index: 7980152 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.4718. Min Act: -0.1700
Data Index: 6850286 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.4405. Min Act: -0.1700
Data Index: 7480274 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.4405. Min Act: -0.1700
Data Index: 8128842 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9718. Min Range: -7.9718
Max Act: 7.4405. Min Act: -0.1700
Data Index: 2514179 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19