Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1137. Min Range: -6.1137
Max Act: 6.1137. Min Act: -0.1700
Data Index: 2699073 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1137. Min Range: -6.1137
Max Act: 6.0824. Min Act: -0.1700
Data Index: 1157959 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1137. Min Range: -6.1137
Max Act: 6.0512. Min Act: -0.1700
Data Index: 8173437 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1137. Min Range: -6.1137
Max Act: 6.0512. Min Act: -0.1700
Data Index: 7038654 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1137. Min Range: -6.1137
Max Act: 6.0199. Min Act: -0.1700
Data Index: 389507 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.9262. Min Act: -0.1700
Data Index: 1433214 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.9262. Min Act: -0.1700
Data Index: 5737174 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8949. Min Act: -0.1700
Data Index: 4425543 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8949. Min Act: -0.1700
Data Index: 3876346 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8949. Min Act: -0.1700
Data Index: 7186863 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8949. Min Act: -0.1700
Data Index: 2392266 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8637. Min Act: -0.1700
Data Index: 2969183 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8949. Min Act: -0.1700
Data Index: 1785447 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8637. Min Act: -0.1700
Data Index: 2542864 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8324. Min Act: -0.1700
Data Index: 1063341 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8324. Min Act: -0.1700
Data Index: 6182533 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8324. Min Act: -0.1700
Data Index: 6944960 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8324. Min Act: -0.1700
Data Index: 2776670 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.8012. Min Act: -0.1700
Data Index: 5196668 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1137. Min Range: -6.1137
Max Act: 5.7699. Min Act: -0.1700
Data Index: 6120121 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19