Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1405 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.7998. Min Act: -0.1700
Data Index: 4182814 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.6435. Min Act: -0.1700
Data Index: 4012558 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.5185. Min Act: -0.1700
Data Index: 5578615 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.2373. Min Act: -0.1700
Data Index: 4249058 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.2373. Min Act: -0.1700
Data Index: 4680145 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.1748. Min Act: -0.1700
Data Index: 508990 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.1435. Min Act: -0.1700
Data Index: 1546954 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.1435. Min Act: -0.1700
Data Index: 484801 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.1123. Min Act: -0.1700
Data Index: 4420129 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.0810. Min Act: -0.1700
Data Index: 8428864 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7998. Min Range: -6.7998
Max Act: 6.0498. Min Act: -0.1700
Data Index: 6156741 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.9873. Min Act: -0.1700
Data Index: 7888870 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.9560. Min Act: -0.1700
Data Index: 8556491 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.9560. Min Act: -0.1700
Data Index: 1544891 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.9560. Min Act: -0.1700
Data Index: 7890883 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.9560. Min Act: -0.1700
Data Index: 5808302 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.9560. Min Act: -0.1700
Data Index: 2293768 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.9248. Min Act: -0.1700
Data Index: 5993454 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.8935. Min Act: -0.1700
Data Index: 287322 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7998. Min Range: -6.7998
Max Act: 5.9248. Min Act: -0.1700
Data Index: 1572655 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19