Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2684. Min Range: -9.2684
Max Act: 9.2684. Min Act: -0.1700
Data Index: 4117774 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2684. Min Range: -9.2684
Max Act: 9.1434. Min Act: -0.1700
Data Index: 5438336 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.6434. Min Act: -0.1700
Data Index: 7038117 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.2684. Min Act: -0.1700
Data Index: 1490384 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.2684. Min Act: -0.1700
Data Index: 6449370 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.2372. Min Act: -0.1700
Data Index: 1862543 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.1122. Min Act: -0.1700
Data Index: 7659110 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.1122. Min Act: -0.1700
Data Index: 2435433 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.0809. Min Act: -0.1700
Data Index: 5101334 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.0184. Min Act: -0.1700
Data Index: 8527335 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2684. Min Range: -9.2684
Max Act: 8.0184. Min Act: -0.1700
Data Index: 6073523 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.9872. Min Act: -0.1700
Data Index: 8320677 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.9872. Min Act: -0.1700
Data Index: 3964022 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.9872. Min Act: -0.1700
Data Index: 1147798 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.8309. Min Act: -0.1700
Data Index: 4516779 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.8309. Min Act: -0.1700
Data Index: 438487 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.7997. Min Act: -0.1700
Data Index: 4060188 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.7684. Min Act: -0.1700
Data Index: 5708279 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.7372. Min Act: -0.1700
Data Index: 5005230 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2684. Min Range: -9.2684
Max Act: 7.7372. Min Act: -0.1700
Data Index: 746788 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19