Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.9617. Min Act: -0.1700
Data Index: 2794964 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.8992. Min Act: -0.1700
Data Index: 4623539 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.5867. Min Act: -0.1700
Data Index: 8455774 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.5867. Min Act: -0.1700
Data Index: 6196007 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.3992. Min Act: -0.1700
Data Index: 818178 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.3367. Min Act: -0.1700
Data Index: 5496567 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.2117. Min Act: -0.1700
Data Index: 182413 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.1492. Min Act: -0.1700
Data Index: 209897 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.1492. Min Act: -0.1700
Data Index: 6487838 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.2117. Min Act: -0.1700
Data Index: 5589814 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.1492. Min Act: -0.1700
Data Index: 3523125 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.0867. Min Act: -0.1700
Data Index: 2302175 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9617. Min Range: -10.9617
Max Act: 9.9617. Min Act: -0.1700
Data Index: 3289311 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.0242. Min Act: -0.1700
Data Index: 1672201 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.0242. Min Act: -0.1700
Data Index: 1815734 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9617. Min Range: -10.9617
Max Act: 10.0242. Min Act: -0.1700
Data Index: 7433778 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9617. Min Range: -10.9617
Max Act: 9.9617. Min Act: -0.1700
Data Index: 5363884 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9617. Min Range: -10.9617
Max Act: 9.9617. Min Act: -0.1700
Data Index: 7945854 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9617. Min Range: -10.9617
Max Act: 9.8992. Min Act: -0.1700
Data Index: 6586281 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9617. Min Range: -10.9617
Max Act: 9.9617. Min Act: -0.1700
Data Index: 412812 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19