Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1751 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.4117. Min Act: -0.1700
Data Index: 3155326 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.4117. Min Act: -0.1700
Data Index: 1833335 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.3805. Min Act: -0.1700
Data Index: 3862616 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.3805. Min Act: -0.1700
Data Index: 4775237 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.3492. Min Act: -0.1700
Data Index: 3650636 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2867. Min Act: -0.1700
Data Index: 6877795 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2867. Min Act: -0.1700
Data Index: 7951785 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.3180. Min Act: -0.1700
Data Index: 554020 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2867. Min Act: -0.1700
Data Index: 3820306 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.3180. Min Act: -0.1700
Data Index: 4247322 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2867. Min Act: -0.1700
Data Index: 5811591 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2555. Min Act: -0.1700
Data Index: 3780783 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2867. Min Act: -0.1700
Data Index: 6841883 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2242. Min Act: -0.1700
Data Index: 39228 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2242. Min Act: -0.1700
Data Index: 7166202 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2555. Min Act: -0.1700
Data Index: 5691591 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2242. Min Act: -0.1700
Data Index: 3438019 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2555. Min Act: -0.1700
Data Index: 5249958 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.2555. Min Act: -0.1700
Data Index: 2660244 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4117. Min Range: -5.4117
Max Act: 5.1930. Min Act: -0.1700
Data Index: 3438018 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19