Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2801 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1127. Min Range: -6.1127
Max Act: 6.1127. Min Act: -0.1700
Data Index: 6901195 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.9565. Min Act: -0.1700
Data Index: 929707 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.8940. Min Act: -0.1700
Data Index: 2677822 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.8627. Min Act: -0.1700
Data Index: 4556685 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.8627. Min Act: -0.1700
Data Index: 5786888 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.8002. Min Act: -0.1700
Data Index: 1440473 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.8002. Min Act: -0.1700
Data Index: 2175409 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.7065. Min Act: -0.1700
Data Index: 6459431 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.6752. Min Act: -0.1700
Data Index: 3880418 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.6440. Min Act: -0.1700
Data Index: 2302728 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.6127. Min Act: -0.1700
Data Index: 1230829 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.5815. Min Act: -0.1700
Data Index: 5913839 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.6127. Min Act: -0.1700
Data Index: 7887860 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.6127. Min Act: -0.1700
Data Index: 7508502 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.6127. Min Act: -0.1700
Data Index: 1544502 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.5502. Min Act: -0.1700
Data Index: 5975020 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.5502. Min Act: -0.1700
Data Index: 4731112 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.5190. Min Act: -0.1700
Data Index: 7183726 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.5502. Min Act: -0.1700
Data Index: 4018903 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1127. Min Range: -6.1127
Max Act: 5.4877. Min Act: -0.1700
Data Index: 3262077 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19