Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0926. Min Range: -7.0926
Max Act: 7.0926. Min Act: -0.1700
Data Index: 5317072 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0926. Min Range: -7.0926
Max Act: 7.0926. Min Act: -0.1700
Data Index: 7766593 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0926. Min Range: -7.0926
Max Act: 7.0613. Min Act: -0.1700
Data Index: 5259057 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.9988. Min Act: -0.1700
Data Index: 7767908 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.9363. Min Act: -0.1700
Data Index: 1211569 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8738. Min Act: -0.1700
Data Index: 6282325 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8738. Min Act: -0.1700
Data Index: 4576264 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8738. Min Act: -0.1700
Data Index: 2147255 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8113. Min Act: -0.1700
Data Index: 4241352 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8113. Min Act: -0.1700
Data Index: 3810777 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6863. Min Act: -0.1700
Data Index: 5669858 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6551. Min Act: -0.1700
Data Index: 6523242 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 1762566 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 555576 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 7728751 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 5388973 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 3143608 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 7605711 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.5926. Min Act: -0.1700
Data Index: 5391199 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.5613. Min Act: -0.1700
Data Index: 2955468 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19