Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1945 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0072. Min Range: -9.0072
Max Act: 9.0072. Min Act: -0.1700
Data Index: 4886831 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0072. Min Range: -9.0072
Max Act: 9.0072. Min Act: -0.1700
Data Index: 6000526 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.9447. Min Act: -0.1700
Data Index: 5726022 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.8197. Min Act: -0.1700
Data Index: 7910420 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.8197. Min Act: -0.1700
Data Index: 7001019 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.8197. Min Act: -0.1700
Data Index: 1807101 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 531972 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.8197. Min Act: -0.1700
Data Index: 2410319 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 6513512 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.8197. Min Act: -0.1700
Data Index: 3938736 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 1066961 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 3682597 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.7572. Min Act: -0.1700
Data Index: 5871606 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 6044212 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 1665013 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 942914 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 676821 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 5369645 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 1664782 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0072. Min Range: -9.0072
Max Act: 8.6947. Min Act: -0.1700
Data Index: 6525104 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19