Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4068 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5419. Min Range: -6.5419
Max Act: 6.5419. Min Act: -0.1700
Data Index: 6556505 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5419. Min Range: -6.5419
Max Act: 6.3857. Min Act: -0.1700
Data Index: 5733711 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5419. Min Range: -6.5419
Max Act: 6.0732. Min Act: -0.1700
Data Index: 5120946 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5419. Min Range: -6.5419
Max Act: 6.0419. Min Act: -0.1700
Data Index: 6867985 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.9482. Min Act: -0.1700
Data Index: 3655368 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.9482. Min Act: -0.1700
Data Index: 4087776 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.9169. Min Act: -0.1700
Data Index: 659876 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.8857. Min Act: -0.1700
Data Index: 5652328 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.8857. Min Act: -0.1700
Data Index: 5174610 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.8544. Min Act: -0.1700
Data Index: 5373312 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.8857. Min Act: -0.1700
Data Index: 5075718 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.8232. Min Act: -0.1700
Data Index: 3827735 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.8544. Min Act: -0.1700
Data Index: 1190117 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.7919. Min Act: -0.1700
Data Index: 2897032 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.7919. Min Act: -0.1700
Data Index: 3501762 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.7919. Min Act: -0.1700
Data Index: 6860452 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.7607. Min Act: -0.1700
Data Index: 4239824 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.7607. Min Act: -0.1700
Data Index: 7315658 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.7607. Min Act: -0.1700
Data Index: 547373 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5419. Min Range: -6.5419
Max Act: 5.7607. Min Act: -0.1700
Data Index: 8034643 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19