Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 131 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.8793. Min Act: -0.1700
Data Index: 405398 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.3793. Min Act: -0.1700
Data Index: 2285773 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.2855. Min Act: -0.1700
Data Index: 5147462 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.1605. Min Act: -0.1700
Data Index: 6625454 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.1918. Min Act: -0.1700
Data Index: 796483 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.1293. Min Act: -0.1700
Data Index: 426008 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.1293. Min Act: -0.1700
Data Index: 8156787 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.1293. Min Act: -0.1700
Data Index: 3494903 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.0980. Min Act: -0.1700
Data Index: 6900720 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.0980. Min Act: -0.1700
Data Index: 2229727 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.1293. Min Act: -0.1700
Data Index: 3500766 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.0980. Min Act: -0.1700
Data Index: 6186494 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.0668. Min Act: -0.1700
Data Index: 2217061 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.0668. Min Act: -0.1700
Data Index: 4554526 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.0668. Min Act: -0.1700
Data Index: 7341764 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8793. Min Range: -7.8793
Max Act: 6.9730. Min Act: -0.1700
Data Index: 2760632 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8793. Min Range: -7.8793
Max Act: 6.9418. Min Act: -0.1700
Data Index: 942636 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8793. Min Range: -7.8793
Max Act: 6.9418. Min Act: -0.1700
Data Index: 4132977 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8793. Min Range: -7.8793
Max Act: 6.9418. Min Act: -0.1700
Data Index: 1209402 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8793. Min Range: -7.8793
Max Act: 6.9418. Min Act: -0.1700
Data Index: 4206798 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19