Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4500 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2655. Min Range: -6.2655
Max Act: 6.2655. Min Act: -0.1700
Data Index: 704287 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2655. Min Range: -6.2655
Max Act: 6.1405. Min Act: -0.1700
Data Index: 8369495 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2655. Min Range: -6.2655
Max Act: 6.0467. Min Act: -0.1700
Data Index: 842526 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.8905. Min Act: -0.1700
Data Index: 7041115 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.8280. Min Act: -0.1700
Data Index: 4491919 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.7967. Min Act: -0.1700
Data Index: 7285756 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.7655. Min Act: -0.1700
Data Index: 7053267 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.7342. Min Act: -0.1700
Data Index: 2385357 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.7342. Min Act: -0.1700
Data Index: 5446661 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.7342. Min Act: -0.1700
Data Index: 794950 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.7342. Min Act: -0.1700
Data Index: 778984 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.7030. Min Act: -0.1700
Data Index: 6226699 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.6717. Min Act: -0.1700
Data Index: 4575016 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.6717. Min Act: -0.1700
Data Index: 5220622 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.6405. Min Act: -0.1700
Data Index: 7261697 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.6405. Min Act: -0.1700
Data Index: 7328912 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.6405. Min Act: -0.1700
Data Index: 5216846 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.6405. Min Act: -0.1700
Data Index: 2162800 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.6092. Min Act: -0.1700
Data Index: 7160208 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2655. Min Range: -6.2655
Max Act: 5.5780. Min Act: -0.1700
Data Index: 4627508 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19