Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1423 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1987. Min Range: -6.1987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 7492225 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1987. Min Range: -6.1987
Max Act: 6.1362. Min Act: -0.1700
Data Index: 2851137 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1987. Min Range: -6.1987
Max Act: 6.1362. Min Act: -0.1700
Data Index: 5080358 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1987. Min Range: -6.1987
Max Act: 6.1362. Min Act: -0.1700
Data Index: 3072858 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1987. Min Range: -6.1987
Max Act: 6.1050. Min Act: -0.1700
Data Index: 4521329 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1987. Min Range: -6.1987
Max Act: 6.0737. Min Act: -0.1700
Data Index: 6786484 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1987. Min Range: -6.1987
Max Act: 6.0112. Min Act: -0.1700
Data Index: 3954049 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.9800. Min Act: -0.1700
Data Index: 3379898 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.9487. Min Act: -0.1700
Data Index: 4116796 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.9487. Min Act: -0.1700
Data Index: 1056406 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.9175. Min Act: -0.1700
Data Index: 7181073 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.8862. Min Act: -0.1700
Data Index: 748637 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5999993 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.8550. Min Act: -0.1700
Data Index: 3045983 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.8550. Min Act: -0.1700
Data Index: 4823678 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5914922 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.8237. Min Act: -0.1700
Data Index: 1207707 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.7925. Min Act: -0.1700
Data Index: 4621121 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.8237. Min Act: -0.1700
Data Index: 3425635 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1987. Min Range: -6.1987
Max Act: 5.8237. Min Act: -0.1700
Data Index: 6996025 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19