Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1982. Min Range: -5.1982
Max Act: 5.1982. Min Act: -0.1700
Data Index: 4637185 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1982. Min Range: -5.1982
Max Act: 5.1357. Min Act: -0.1700
Data Index: 4747286 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.9170. Min Act: -0.1700
Data Index: 6100748 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.9170. Min Act: -0.1700
Data Index: 8215780 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.8545. Min Act: -0.1700
Data Index: 333377 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.8232. Min Act: -0.1700
Data Index: 8538193 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.7607. Min Act: -0.1700
Data Index: 6632760 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.7295. Min Act: -0.1700
Data Index: 7609308 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6982. Min Act: -0.1700
Data Index: 5326139 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6982. Min Act: -0.1700
Data Index: 6773494 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6670. Min Act: -0.1700
Data Index: 6247784 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6982. Min Act: -0.1700
Data Index: 7668183 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6670. Min Act: -0.1700
Data Index: 5365796 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6670. Min Act: -0.1700
Data Index: 4922863 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6357. Min Act: -0.1700
Data Index: 5137874 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6357. Min Act: -0.1700
Data Index: 6309008 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6357. Min Act: -0.1700
Data Index: 4155734 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6045. Min Act: -0.1700
Data Index: 7430336 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6045. Min Act: -0.1700
Data Index: 7174425 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1982. Min Range: -5.1982
Max Act: 4.6045. Min Act: -0.1700
Data Index: 2163064 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19