Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1649 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.9056. Min Act: -0.1700
Data Index: 7835126 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8744. Min Act: -0.1700
Data Index: 5981707 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8744. Min Act: -0.1700
Data Index: 704065 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8431. Min Act: -0.1700
Data Index: 3993305 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8119. Min Act: -0.1700
Data Index: 8464254 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8119. Min Act: -0.1700
Data Index: 8248207 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 1495405 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 3293917 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 4228586 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 2764775 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7494. Min Act: -0.1700
Data Index: 1454777 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7494. Min Act: -0.1700
Data Index: 2379362 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7494. Min Act: -0.1700
Data Index: 561060 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7181. Min Act: -0.1700
Data Index: 3043804 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7181. Min Act: -0.1700
Data Index: 623278 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6556. Min Act: -0.1700
Data Index: 5965467 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6556. Min Act: -0.1700
Data Index: 5972241 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6556. Min Act: -0.1700
Data Index: 499859 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6244. Min Act: -0.1700
Data Index: 6903526 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6244. Min Act: -0.1700
Data Index: 4683040 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19