Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2648. Min Range: -8.2648
Max Act: 8.2648. Min Act: -0.1700
Data Index: 3967659 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2648. Min Range: -8.2648
Max Act: 8.0773. Min Act: -0.1700
Data Index: 6776057 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2648. Min Range: -8.2648
Max Act: 8.0148. Min Act: -0.1700
Data Index: 5393121 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2648. Min Range: -8.2648
Max Act: 8.0461. Min Act: -0.1700
Data Index: 4060736 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2648. Min Range: -8.2648
Max Act: 8.0148. Min Act: -0.1700
Data Index: 2504855 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.9523. Min Act: -0.1700
Data Index: 8462803 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.8273. Min Act: -0.1700
Data Index: 4001898 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.8586. Min Act: -0.1700
Data Index: 4060735 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.7961. Min Act: -0.1700
Data Index: 7759894 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.8273. Min Act: -0.1700
Data Index: 4621275 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.8273. Min Act: -0.1700
Data Index: 827025 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.7961. Min Act: -0.1700
Data Index: 4292082 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.7023. Min Act: -0.1700
Data Index: 1696644 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.7023. Min Act: -0.1700
Data Index: 6230888 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.7023. Min Act: -0.1700
Data Index: 1917360 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.6711. Min Act: -0.1700
Data Index: 6759667 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.7023. Min Act: -0.1700
Data Index: 5316935 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 6449107 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 6776058 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2648. Min Range: -8.2648
Max Act: 7.6086. Min Act: -0.1700
Data Index: 4001897 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19