Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.7537. Min Act: -0.1700
Data Index: 6543742 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.5037. Min Act: -0.1700
Data Index: 419774 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.4412. Min Act: -0.1700
Data Index: 4189053 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.2537. Min Act: -0.1700
Data Index: 4306719 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.2537. Min Act: -0.1700
Data Index: 5753187 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.2537. Min Act: -0.1700
Data Index: 1266019 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.1912. Min Act: -0.1700
Data Index: 4369658 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.1287. Min Act: -0.1700
Data Index: 8345756 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.1287. Min Act: -0.1700
Data Index: 5017820 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.1287. Min Act: -0.1700
Data Index: 514666 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0662. Min Act: -0.1700
Data Index: 2824646 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0662. Min Act: -0.1700
Data Index: 6982622 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0037. Min Act: -0.1700
Data Index: 5119534 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0037. Min Act: -0.1700
Data Index: 5011360 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0037. Min Act: -0.1700
Data Index: 6601992 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0037. Min Act: -0.1700
Data Index: 7766818 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7537. Min Range: -8.7537
Max Act: 7.9412. Min Act: -0.1700
Data Index: 701913 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0037. Min Act: -0.1700
Data Index: 2181233 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0037. Min Act: -0.1700
Data Index: 4430455 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7537. Min Range: -8.7537
Max Act: 8.0037. Min Act: -0.1700
Data Index: 4932817 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19