Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2217 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4015. Min Range: -8.4015
Max Act: 8.4015. Min Act: -0.1700
Data Index: 1053289 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4015. Min Range: -8.4015
Max Act: 8.0265. Min Act: -0.1700
Data Index: 2601682 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.8702. Min Act: -0.1700
Data Index: 8324881 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.7452. Min Act: -0.1700
Data Index: 2978611 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.7452. Min Act: -0.1700
Data Index: 4966445 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.6827. Min Act: -0.1700
Data Index: 2877296 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.6827. Min Act: -0.1700
Data Index: 7935513 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.6827. Min Act: -0.1700
Data Index: 3753115 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.6515. Min Act: -0.1700
Data Index: 413577 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.6515. Min Act: -0.1700
Data Index: 3048043 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.5890. Min Act: -0.1700
Data Index: 4976201 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.5890. Min Act: -0.1700
Data Index: 6152521 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.5890. Min Act: -0.1700
Data Index: 956745 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.5577. Min Act: -0.1700
Data Index: 4495215 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.5577. Min Act: -0.1700
Data Index: 6159941 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.5265. Min Act: -0.1700
Data Index: 7569083 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.4952. Min Act: -0.1700
Data Index: 1341739 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.5265. Min Act: -0.1700
Data Index: 8331449 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.4952. Min Act: -0.1700
Data Index: 6873086 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4015. Min Range: -8.4015
Max Act: 7.4952. Min Act: -0.1700
Data Index: 4539396 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19