Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4749 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1754. Min Range: -7.1754
Max Act: 7.1754. Min Act: -0.1700
Data Index: 7756730 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1754. Min Range: -7.1754
Max Act: 7.0191. Min Act: -0.1700
Data Index: 6329391 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1754. Min Range: -7.1754
Max Act: 7.0191. Min Act: -0.1700
Data Index: 5373294 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.9566. Min Act: -0.1700
Data Index: 5002548 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.8004. Min Act: -0.1700
Data Index: 3226416 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.7691. Min Act: -0.1700
Data Index: 8575427 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.7066. Min Act: -0.1700
Data Index: 4584764 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.7379. Min Act: -0.1700
Data Index: 8128809 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.6129. Min Act: -0.1700
Data Index: 6510275 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.5816. Min Act: -0.1700
Data Index: 5226902 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.5816. Min Act: -0.1700
Data Index: 4246130 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.5504. Min Act: -0.1700
Data Index: 6331479 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.5191. Min Act: -0.1700
Data Index: 2045414 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.4879. Min Act: -0.1700
Data Index: 3324208 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.4879. Min Act: -0.1700
Data Index: 5345173 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.4566. Min Act: -0.1700
Data Index: 1748911 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.4566. Min Act: -0.1700
Data Index: 379801 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.4254. Min Act: -0.1700
Data Index: 5428754 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.4566. Min Act: -0.1700
Data Index: 6747249 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1754. Min Range: -7.1754
Max Act: 6.4254. Min Act: -0.1700
Data Index: 6195036 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19