Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.9063. Min Act: -0.1700
Data Index: 740109 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.4063. Min Act: -0.1700
Data Index: 2579934 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.3126. Min Act: -0.1700
Data Index: 2173473 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.2813. Min Act: -0.1700
Data Index: 8241961 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.2501. Min Act: -0.1700
Data Index: 4999151 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.1876. Min Act: -0.1700
Data Index: 4841966 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.1876. Min Act: -0.1700
Data Index: 8104382 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.1563. Min Act: -0.1700
Data Index: 7343948 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.1251. Min Act: -0.1700
Data Index: 395777 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9063. Min Range: -6.9063
Max Act: 6.0938. Min Act: -0.1700
Data Index: 2580069 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.9688. Min Act: -0.1700
Data Index: 7847535 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.9376. Min Act: -0.1700
Data Index: 7575022 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.9376. Min Act: -0.1700
Data Index: 8175919 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.9376. Min Act: -0.1700
Data Index: 6713937 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.8751. Min Act: -0.1700
Data Index: 395915 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.8751. Min Act: -0.1700
Data Index: 4655122 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.9063. Min Act: -0.1700
Data Index: 2263516 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.8751. Min Act: -0.1700
Data Index: 8500499 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.8751. Min Act: -0.1700
Data Index: 3474763 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9063. Min Range: -6.9063
Max Act: 5.9063. Min Act: -0.1700
Data Index: 2369927 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19