Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 157 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8545. Min Range: -8.8545
Max Act: 8.8545. Min Act: -0.1700
Data Index: 330201 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8545. Min Range: -8.8545
Max Act: 8.6045. Min Act: -0.1700
Data Index: 8426141 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8545. Min Range: -8.8545
Max Act: 8.2295. Min Act: -0.1700
Data Index: 806466 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8545. Min Range: -8.8545
Max Act: 8.2295. Min Act: -0.1700
Data Index: 8319891 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8545. Min Range: -8.8545
Max Act: 8.1045. Min Act: -0.1700
Data Index: 8729631 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8545. Min Range: -8.8545
Max Act: 8.0107. Min Act: -0.1700
Data Index: 2252163 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.9795. Min Act: -0.1700
Data Index: 8091993 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.9482. Min Act: -0.1700
Data Index: 8258308 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.9482. Min Act: -0.1700
Data Index: 6471658 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.8857. Min Act: -0.1700
Data Index: 1502939 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.8545. Min Act: -0.1700
Data Index: 1506207 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.8545. Min Act: -0.1700
Data Index: 4124330 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.8232. Min Act: -0.1700
Data Index: 256627 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.8232. Min Act: -0.1700
Data Index: 8349447 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.8232. Min Act: -0.1700
Data Index: 8426142 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.7607. Min Act: -0.1700
Data Index: 1232966 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.7920. Min Act: -0.1700
Data Index: 1004733 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.7607. Min Act: -0.1700
Data Index: 6736790 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.6982. Min Act: -0.1700
Data Index: 6513856 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8545. Min Range: -8.8545
Max Act: 7.7295. Min Act: -0.1700
Data Index: 6057566 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19