Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5378 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.9015. Min Act: -0.1700
Data Index: 2047610 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.5890. Min Act: -0.1700
Data Index: 4194769 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.5890. Min Act: -0.1700
Data Index: 3456209 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.5577. Min Act: -0.1700
Data Index: 3374898 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.5265. Min Act: -0.1700
Data Index: 1399717 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.5265. Min Act: -0.1700
Data Index: 3382119 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.4327. Min Act: -0.1700
Data Index: 7256247 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.4015. Min Act: -0.1700
Data Index: 5143036 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.4015. Min Act: -0.1700
Data Index: 1107874 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.3390. Min Act: -0.1700
Data Index: 2999492 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.3077. Min Act: -0.1700
Data Index: 7450290 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.3077. Min Act: -0.1700
Data Index: 8563769 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.2765. Min Act: -0.1700
Data Index: 6194353 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.2765. Min Act: -0.1700
Data Index: 2147405 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.2765. Min Act: -0.1700
Data Index: 62417 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.2452. Min Act: -0.1700
Data Index: 2996610 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.2452. Min Act: -0.1700
Data Index: 4445728 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.1827. Min Act: -0.1700
Data Index: 5343423 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.1827. Min Act: -0.1700
Data Index: 4895124 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9015. Min Range: -7.9015
Max Act: 7.1827. Min Act: -0.1700
Data Index: 7572052 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19