Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1722 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3423. Min Range: -9.3423
Max Act: 9.3423. Min Act: -0.1700
Data Index: 1249816 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3423. Min Range: -9.3423
Max Act: 9.2173. Min Act: -0.1700
Data Index: 4989942 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3423. Min Range: -9.3423
Max Act: 9.0298. Min Act: -0.1700
Data Index: 6804042 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3423. Min Range: -9.3423
Max Act: 9.0298. Min Act: -0.1700
Data Index: 4588665 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3423. Min Range: -9.3423
Max Act: 9.0298. Min Act: -0.1700
Data Index: 8161654 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.9673. Min Act: -0.1700
Data Index: 5629608 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.9673. Min Act: -0.1700
Data Index: 3012537 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.9048. Min Act: -0.1700
Data Index: 5731636 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.9048. Min Act: -0.1700
Data Index: 1689079 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.9048. Min Act: -0.1700
Data Index: 4816967 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.8423. Min Act: -0.1700
Data Index: 8616572 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.8423. Min Act: -0.1700
Data Index: 1177411 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.8423. Min Act: -0.1700
Data Index: 2044398 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.8423. Min Act: -0.1700
Data Index: 4598373 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.8423. Min Act: -0.1700
Data Index: 7257229 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.8423. Min Act: -0.1700
Data Index: 7094154 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.7798. Min Act: -0.1700
Data Index: 6702636 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.7173. Min Act: -0.1700
Data Index: 741360 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.7173. Min Act: -0.1700
Data Index: 6066602 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3423. Min Range: -9.3423
Max Act: 8.7173. Min Act: -0.1700
Data Index: 6490820 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19