Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1382 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1673. Min Range: -7.1673
Max Act: 7.1673. Min Act: -0.1700
Data Index: 5698802 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.9173. Min Act: -0.1700
Data Index: 4801969 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.7923. Min Act: -0.1700
Data Index: 6454504 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.7923. Min Act: -0.1700
Data Index: 6331022 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.7298. Min Act: -0.1700
Data Index: 4220593 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.6985. Min Act: -0.1700
Data Index: 5790921 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.6985. Min Act: -0.1700
Data Index: 1121654 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.6673. Min Act: -0.1700
Data Index: 3089164 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.6673. Min Act: -0.1700
Data Index: 704284 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.6048. Min Act: -0.1700
Data Index: 1518579 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.6048. Min Act: -0.1700
Data Index: 2723828 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.5735. Min Act: -0.1700
Data Index: 813099 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.5735. Min Act: -0.1700
Data Index: 480340 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.5423. Min Act: -0.1700
Data Index: 1859452 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.5110. Min Act: -0.1700
Data Index: 6443403 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.4798. Min Act: -0.1700
Data Index: 2703851 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.4798. Min Act: -0.1700
Data Index: 1017465 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.4798. Min Act: -0.1700
Data Index: 1527506 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.4173. Min Act: -0.1700
Data Index: 5016928 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1673. Min Range: -7.1673
Max Act: 6.4173. Min Act: -0.1700
Data Index: 2826985 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19