Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5245 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.8449. Min Act: -0.1700
Data Index: 1318324 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.6887. Min Act: -0.1700
Data Index: 8382775 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.6574. Min Act: -0.1700
Data Index: 3080785 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.5324. Min Act: -0.1700
Data Index: 2374899 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.5012. Min Act: -0.1700
Data Index: 8688174 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.4699. Min Act: -0.1700
Data Index: 8518956 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.5012. Min Act: -0.1700
Data Index: 2634003 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.4699. Min Act: -0.1700
Data Index: 8507183 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.4387. Min Act: -0.1700
Data Index: 2951235 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.4074. Min Act: -0.1700
Data Index: 701613 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.4387. Min Act: -0.1700
Data Index: 2302314 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.4387. Min Act: -0.1700
Data Index: 4558128 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.3449. Min Act: -0.1700
Data Index: 8457838 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.3449. Min Act: -0.1700
Data Index: 5426082 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.3762. Min Act: -0.1700
Data Index: 2068578 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.3449. Min Act: -0.1700
Data Index: 1664233 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.3137. Min Act: -0.1700
Data Index: 6269029 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.3137. Min Act: -0.1700
Data Index: 671808 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.3449. Min Act: -0.1700
Data Index: 3909761 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8449. Min Range: -6.8449
Max Act: 6.3137. Min Act: -0.1700
Data Index: 7945298 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19