Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2542 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6465. Min Range: -12.6465
Max Act: 12.6465. Min Act: -0.1700
Data Index: 788169 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6465. Min Range: -12.6465
Max Act: 12.3965. Min Act: -0.1700
Data Index: 3713071 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6465. Min Range: -12.6465
Max Act: 12.2715. Min Act: -0.1700
Data Index: 5839798 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6465. Min Range: -12.6465
Max Act: 12.0215. Min Act: -0.1698
Data Index: 5307263 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.8965. Min Act: -0.1696
Data Index: 3840706 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.8965. Min Act: -0.1700
Data Index: 7780972 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.8965. Min Act: -0.1700
Data Index: 8636809 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.8965. Min Act: -0.1700
Data Index: 4504849 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.8965. Min Act: -0.1700
Data Index: 8590707 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.8340. Min Act: -0.1700
Data Index: 5314077 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.8340. Min Act: -0.1700
Data Index: 3392003 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.8340. Min Act: -0.1700
Data Index: 2249718 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.7715. Min Act: -0.1700
Data Index: 8532545 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.7090. Min Act: -0.1700
Data Index: 6509676 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.7090. Min Act: -0.1700
Data Index: 5798015 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.7090. Min Act: -0.1700
Data Index: 5225263 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.7090. Min Act: -0.1700
Data Index: 3175660 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.6465. Min Act: -0.1700
Data Index: 2767421 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.6465. Min Act: -0.1700
Data Index: 978281 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6465. Min Range: -12.6465
Max Act: 11.7090. Min Act: -0.1700
Data Index: 2021036 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19