Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 759 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2581. Min Range: -8.2581
Max Act: 8.2581. Min Act: -0.1700
Data Index: 8250539 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2581. Min Range: -8.2581
Max Act: 8.1956. Min Act: -0.1700
Data Index: 3128265 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.9456. Min Act: -0.1700
Data Index: 2003650 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.9456. Min Act: -0.1700
Data Index: 8769599 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.8831. Min Act: -0.1700
Data Index: 1357155 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.8831. Min Act: -0.1700
Data Index: 7923590 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.8831. Min Act: -0.1700
Data Index: 1447890 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.8206. Min Act: -0.1700
Data Index: 4362933 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.8206. Min Act: -0.1700
Data Index: 529233 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.8206. Min Act: -0.1700
Data Index: 5791804 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.7581. Min Act: -0.1700
Data Index: 5086964 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.7581. Min Act: -0.1700
Data Index: 6655549 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.7581. Min Act: -0.1700
Data Index: 3137025 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.7581. Min Act: -0.1700
Data Index: 3750331 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.7581. Min Act: -0.1700
Data Index: 6655547 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.6956. Min Act: -0.1700
Data Index: 4173590 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.6956. Min Act: -0.1700
Data Index: 4123461 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.6956. Min Act: -0.1700
Data Index: 8117859 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.6956. Min Act: -0.1700
Data Index: 7491978 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2581. Min Range: -8.2581
Max Act: 7.6644. Min Act: -0.1700
Data Index: 2803276 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19