Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2380 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7719. Min Range: -9.7719
Max Act: 9.7719. Min Act: -0.1700
Data Index: 130369 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7719. Min Range: -9.7719
Max Act: 9.5844. Min Act: -0.1700
Data Index: 5450352 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7719. Min Range: -9.7719
Max Act: 9.3344. Min Act: -0.1700
Data Index: 6416944 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7719. Min Range: -9.7719
Max Act: 9.2094. Min Act: -0.1700
Data Index: 484496 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7719. Min Range: -9.7719
Max Act: 9.0219. Min Act: -0.1700
Data Index: 2251176 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.9594. Min Act: -0.1700
Data Index: 3192893 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7719. Min Range: -9.7719
Max Act: 9.0219. Min Act: -0.1700
Data Index: 7030916 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.9594. Min Act: -0.1700
Data Index: 4608132 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.9594. Min Act: -0.1700
Data Index: 4078895 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.8969. Min Act: -0.1700
Data Index: 2393604 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.8344. Min Act: -0.1700
Data Index: 2856609 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.8344. Min Act: -0.1700
Data Index: 5908630 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.7719. Min Act: -0.1700
Data Index: 384486 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.7719. Min Act: -0.1700
Data Index: 1053309 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.7719. Min Act: -0.1700
Data Index: 7558102 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.7094. Min Act: -0.1700
Data Index: 7945866 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.6469. Min Act: -0.1700
Data Index: 7558103 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.6469. Min Act: -0.1700
Data Index: 3933136 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.6469. Min Act: -0.1700
Data Index: 1814743 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7719. Min Range: -9.7719
Max Act: 8.6469. Min Act: -0.1700
Data Index: 1207582 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19