Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0454. Min Range: -7.0454
Max Act: 7.0454. Min Act: -0.1700
Data Index: 5721502 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.9517. Min Act: -0.1700
Data Index: 265904 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.6392. Min Act: -0.1700
Data Index: 7834933 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.6392. Min Act: -0.1700
Data Index: 4101802 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.6392. Min Act: -0.1700
Data Index: 1310653 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.4517. Min Act: -0.1700
Data Index: 8386887 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.3892. Min Act: -0.1700
Data Index: 4663547 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.3579. Min Act: -0.1700
Data Index: 7986012 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.2954. Min Act: -0.1700
Data Index: 5468932 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.2954. Min Act: -0.1700
Data Index: 931069 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.2017. Min Act: -0.1700
Data Index: 5445035 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.2017. Min Act: -0.1700
Data Index: 6435651 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.1392. Min Act: -0.1700
Data Index: 8504050 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.1392. Min Act: -0.1700
Data Index: 8434092 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.1392. Min Act: -0.1700
Data Index: 5819807 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.1079. Min Act: -0.1700
Data Index: 7295932 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.1079. Min Act: -0.1700
Data Index: 5502131 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.1079. Min Act: -0.1700
Data Index: 4964117 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.0767. Min Act: -0.1700
Data Index: 8201214 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0454. Min Range: -7.0454
Max Act: 6.0767. Min Act: -0.1700
Data Index: 5646586 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19