Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2065. Min Range: -6.2065
Max Act: 6.2065. Min Act: -0.1700
Data Index: 6258818 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2065. Min Range: -6.2065
Max Act: 6.1440. Min Act: -0.1700
Data Index: 4089281 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.8002. Min Act: -0.1700
Data Index: 7445814 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.7690. Min Act: -0.1700
Data Index: 1115401 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.7690. Min Act: -0.1700
Data Index: 3576434 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.7377. Min Act: -0.1700
Data Index: 1875294 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.7065. Min Act: -0.1700
Data Index: 7941688 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6752. Min Act: -0.1700
Data Index: 3035552 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6440. Min Act: -0.1700
Data Index: 1552551 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6440. Min Act: -0.1700
Data Index: 8345851 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6440. Min Act: -0.1700
Data Index: 8169926 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6440. Min Act: -0.1700
Data Index: 6859527 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6440. Min Act: -0.1700
Data Index: 6738803 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6440. Min Act: -0.1700
Data Index: 878830 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6440. Min Act: -0.1700
Data Index: 4010785 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6440. Min Act: -0.1700
Data Index: 4232679 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.6127. Min Act: -0.1700
Data Index: 5141365 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.5815. Min Act: -0.1700
Data Index: 6198782 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.5815. Min Act: -0.1700
Data Index: 4490738 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2065. Min Range: -6.2065
Max Act: 5.5815. Min Act: -0.1700
Data Index: 3040684 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19