Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.6414. Min Act: -0.1700
Data Index: 2440931 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.5789. Min Act: -0.1700
Data Index: 7532582 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.5164. Min Act: -0.1700
Data Index: 4984031 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.5164. Min Act: -0.1700
Data Index: 3216096 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.5164. Min Act: -0.1700
Data Index: 3512638 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.5164. Min Act: -0.1700
Data Index: 4359390 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4852. Min Act: -0.1700
Data Index: 6625378 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4852. Min Act: -0.1700
Data Index: 5268778 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4539. Min Act: -0.1700
Data Index: 6539465 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4852. Min Act: -0.1700
Data Index: 8767610 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4539. Min Act: -0.1700
Data Index: 1074239 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4227. Min Act: -0.1700
Data Index: 3530819 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4539. Min Act: -0.1700
Data Index: 3593832 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4227. Min Act: -0.1700
Data Index: 3777159 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4227. Min Act: -0.1700
Data Index: 7245432 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.4227. Min Act: -0.1700
Data Index: 4047298 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.3914. Min Act: -0.1700
Data Index: 4921652 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.3914. Min Act: -0.1700
Data Index: 1385104 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.3602. Min Act: -0.1700
Data Index: 329936 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6414. Min Range: -7.6414
Max Act: 7.3289. Min Act: -0.1700
Data Index: 6947612 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19