Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1392. Min Range: -7.1392
Max Act: 7.1392. Min Act: -0.1700
Data Index: 4275449 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1392. Min Range: -7.1392
Max Act: 7.0454. Min Act: -0.1700
Data Index: 5996706 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1392. Min Range: -7.1392
Max Act: 7.0767. Min Act: -0.1700
Data Index: 5378831 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1392. Min Range: -7.1392
Max Act: 7.0454. Min Act: -0.1700
Data Index: 5531393 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1392. Min Range: -7.1392
Max Act: 7.0142. Min Act: -0.1700
Data Index: 5576436 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1392. Min Range: -7.1392
Max Act: 7.0142. Min Act: -0.1700
Data Index: 1219600 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9829. Min Act: -0.1700
Data Index: 4140779 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9829. Min Act: -0.1700
Data Index: 348762 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9829. Min Act: -0.1700
Data Index: 7011672 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9517. Min Act: -0.1700
Data Index: 6069641 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9517. Min Act: -0.1700
Data Index: 3776965 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9517. Min Act: -0.1700
Data Index: 4478709 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9204. Min Act: -0.1700
Data Index: 3080164 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9204. Min Act: -0.1700
Data Index: 5235515 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.8892. Min Act: -0.1700
Data Index: 7662644 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9204. Min Act: -0.1700
Data Index: 573717 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.9204. Min Act: -0.1700
Data Index: 528002 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.8579. Min Act: -0.1700
Data Index: 6812865 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.8579. Min Act: -0.1700
Data Index: 7835520 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1392. Min Range: -7.1392
Max Act: 6.8892. Min Act: -0.1700
Data Index: 3639017 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19