Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5074 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3797. Min Range: -7.3797
Max Act: 7.3797. Min Act: -0.1700
Data Index: 1885700 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3797. Min Range: -7.3797
Max Act: 7.1922. Min Act: -0.1700
Data Index: 2548457 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3797. Min Range: -7.3797
Max Act: 7.0984. Min Act: -0.1700
Data Index: 2687405 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3797. Min Range: -7.3797
Max Act: 7.0672. Min Act: -0.1700
Data Index: 6370426 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3797. Min Range: -7.3797
Max Act: 7.0672. Min Act: -0.1700
Data Index: 3823485 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3797. Min Range: -7.3797
Max Act: 7.0359. Min Act: -0.1700
Data Index: 5232003 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.9422. Min Act: -0.1700
Data Index: 7377861 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.9422. Min Act: -0.1700
Data Index: 5374057 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.9422. Min Act: -0.1700
Data Index: 3201193 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.9109. Min Act: -0.1700
Data Index: 6773137 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.9109. Min Act: -0.1700
Data Index: 3574375 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.9109. Min Act: -0.1700
Data Index: 7159382 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.9109. Min Act: -0.1700
Data Index: 6190247 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.8484. Min Act: -0.1700
Data Index: 6517177 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.8172. Min Act: -0.1700
Data Index: 4311971 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.8172. Min Act: -0.1700
Data Index: 8467160 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.8172. Min Act: -0.1700
Data Index: 7463172 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.7859. Min Act: -0.1700
Data Index: 3275169 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.7547. Min Act: -0.1700
Data Index: 5568791 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3797. Min Range: -7.3797
Max Act: 6.8172. Min Act: -0.1700
Data Index: 7362755 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19