Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0170. Min Range: -7.0170
Max Act: 7.0170. Min Act: -0.1700
Data Index: 7836080 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.9858. Min Act: -0.1700
Data Index: 6932915 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.9233. Min Act: -0.1700
Data Index: 8361152 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.8920. Min Act: -0.1700
Data Index: 2704662 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.8608. Min Act: -0.1700
Data Index: 6932909 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.8920. Min Act: -0.1700
Data Index: 6932921 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.7670. Min Act: -0.1700
Data Index: 6932904 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.7983. Min Act: -0.1700
Data Index: 6932924 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.7358. Min Act: -0.1700
Data Index: 6932903 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.7358. Min Act: -0.1700
Data Index: 6932901 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.6733. Min Act: -0.1700
Data Index: 6932923 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.7045. Min Act: -0.1700
Data Index: 6932910 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.6733. Min Act: -0.1700
Data Index: 2704660 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.6733. Min Act: -0.1700
Data Index: 6932918 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.5795. Min Act: -0.1700
Data Index: 6932905 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.5795. Min Act: -0.1700
Data Index: 893833 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.5170. Min Act: -0.1700
Data Index: 6932908 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.4545. Min Act: -0.1700
Data Index: 3032314 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.4858. Min Act: -0.1700
Data Index: 8361153 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0170. Min Range: -7.0170
Max Act: 6.4545. Min Act: -0.1700
Data Index: 6932900 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19