Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1823 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.7395. Min Act: -0.1700
Data Index: 874697 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.7395. Min Act: -0.1700
Data Index: 6813556 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.6458. Min Act: -0.1700
Data Index: 3253908 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.6458. Min Act: -0.1700
Data Index: 8354149 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.6145. Min Act: -0.1700
Data Index: 7638922 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.5833. Min Act: -0.1700
Data Index: 7181147 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.5520. Min Act: -0.1700
Data Index: 3526835 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.5520. Min Act: -0.1700
Data Index: 1555754 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.5208. Min Act: -0.1700
Data Index: 4405121 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.4895. Min Act: -0.1700
Data Index: 4126304 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.4895. Min Act: -0.1700
Data Index: 3823012 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.4583. Min Act: -0.1700
Data Index: 6194592 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.4270. Min Act: -0.1700
Data Index: 2051631 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.4270. Min Act: -0.1700
Data Index: 604646 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.3958. Min Act: -0.1700
Data Index: 5808584 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.3645. Min Act: -0.1700
Data Index: 6683544 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.4270. Min Act: -0.1700
Data Index: 4289608 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.3958. Min Act: -0.1700
Data Index: 2747310 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.3645. Min Act: -0.1700
Data Index: 1577590 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7395. Min Range: -6.7395
Max Act: 6.3645. Min Act: -0.1700
Data Index: 2551321 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19