Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5570 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0924. Min Range: -7.0924
Max Act: 7.0924. Min Act: -0.1700
Data Index: 4627674 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0924. Min Range: -7.0924
Max Act: 7.0299. Min Act: -0.1700
Data Index: 5353455 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0924. Min Range: -7.0924
Max Act: 7.0299. Min Act: -0.1700
Data Index: 2138590 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.9361. Min Act: -0.1700
Data Index: 1675035 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.9674. Min Act: -0.1700
Data Index: 5547839 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.9049. Min Act: -0.1700
Data Index: 6830076 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.9049. Min Act: -0.1700
Data Index: 5547838 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.9049. Min Act: -0.1700
Data Index: 346954 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.8736. Min Act: -0.1700
Data Index: 5353454 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.8424. Min Act: -0.1700
Data Index: 409071 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.8736. Min Act: -0.1700
Data Index: 6830075 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.8424. Min Act: -0.1700
Data Index: 4257899 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.8111. Min Act: -0.1700
Data Index: 4257898 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.8111. Min Act: -0.1700
Data Index: 2610795 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.8111. Min Act: -0.1700
Data Index: 1812537 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.7799. Min Act: -0.1700
Data Index: 7695543 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.7486. Min Act: -0.1700
Data Index: 346953 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.7486. Min Act: -0.1700
Data Index: 1675037 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.6549. Min Act: -0.1700
Data Index: 712268 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0924. Min Range: -7.0924
Max Act: 6.5611. Min Act: -0.1700
Data Index: 2610794 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19