Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.7708. Min Act: -0.1700
Data Index: 3640461 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.7708. Min Act: -0.1700
Data Index: 8723728 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.7396. Min Act: -0.1700
Data Index: 2174767 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.7083. Min Act: -0.1700
Data Index: 3840869 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.6771. Min Act: -0.1700
Data Index: 6314809 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.6146. Min Act: -0.1700
Data Index: 4011273 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.5833. Min Act: -0.1700
Data Index: 1445470 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.6146. Min Act: -0.1700
Data Index: 5262329 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.6146. Min Act: -0.1700
Data Index: 4705787 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.5521. Min Act: -0.1700
Data Index: 4934817 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.5208. Min Act: -0.1700
Data Index: 7337358 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.4896. Min Act: -0.1700
Data Index: 1689333 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.4896. Min Act: -0.1700
Data Index: 6395694 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.4583. Min Act: -0.1700
Data Index: 2798804 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.4583. Min Act: -0.1700
Data Index: 6957043 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.4896. Min Act: -0.1700
Data Index: 5417917 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.4583. Min Act: -0.1700
Data Index: 6791166 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.4271. Min Act: -0.1700
Data Index: 2015891 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.4271. Min Act: -0.1700
Data Index: 1949490 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7708. Min Range: -5.7708
Max Act: 5.3958. Min Act: -0.1700
Data Index: 5274972 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19