Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4605 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0023. Min Range: -6.0023
Max Act: 6.0023. Min Act: -0.1700
Data Index: 3610745 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.9398. Min Act: -0.1700
Data Index: 4416894 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8773. Min Act: -0.1700
Data Index: 4416887 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.9085. Min Act: -0.1700
Data Index: 636084 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8773. Min Act: -0.1700
Data Index: 5126969 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8773. Min Act: -0.1700
Data Index: 4618996 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8460. Min Act: -0.1700
Data Index: 4416886 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8460. Min Act: -0.1700
Data Index: 4416882 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8460. Min Act: -0.1700
Data Index: 4416890 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8460. Min Act: -0.1700
Data Index: 4416889 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8460. Min Act: -0.1700
Data Index: 1409619 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8148. Min Act: -0.1700
Data Index: 4416879 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8148. Min Act: -0.1700
Data Index: 3645714 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.8148. Min Act: -0.1700
Data Index: 4416884 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.7835. Min Act: -0.1700
Data Index: 6817557 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.7835. Min Act: -0.1700
Data Index: 4416880 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.7835. Min Act: -0.1700
Data Index: 4416893 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.7835. Min Act: -0.1700
Data Index: 5732345 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.7835. Min Act: -0.1700
Data Index: 4416892 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0023. Min Range: -6.0023
Max Act: 5.7523. Min Act: -0.1700
Data Index: 1338313 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19