Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 712 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3581. Min Range: -7.3581
Max Act: 7.3581. Min Act: -0.1700
Data Index: 331856 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3581. Min Range: -7.3581
Max Act: 7.3269. Min Act: -0.1700
Data Index: 4487414 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3581. Min Range: -7.3581
Max Act: 7.1706. Min Act: -0.1700
Data Index: 7576458 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3581. Min Range: -7.3581
Max Act: 7.1706. Min Act: -0.1700
Data Index: 8587892 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.9519. Min Act: -0.1700
Data Index: 6692772 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.8894. Min Act: -0.1700
Data Index: 1454293 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.8581. Min Act: -0.1700
Data Index: 2785599 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.8581. Min Act: -0.1700
Data Index: 2472009 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.8269. Min Act: -0.1700
Data Index: 1265002 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.7956. Min Act: -0.1700
Data Index: 7573097 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.8269. Min Act: -0.1700
Data Index: 205106 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.7331. Min Act: -0.1700
Data Index: 6008533 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.7019. Min Act: -0.1700
Data Index: 3598925 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.7331. Min Act: -0.1700
Data Index: 1943709 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.6706. Min Act: -0.1700
Data Index: 5600539 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.6394. Min Act: -0.1700
Data Index: 6053150 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.5769. Min Act: -0.1700
Data Index: 6999462 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.6081. Min Act: -0.1700
Data Index: 250019 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.5769. Min Act: -0.1700
Data Index: 5082549 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3581. Min Range: -7.3581
Max Act: 6.6081. Min Act: -0.1700
Data Index: 53828 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19