Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4654. Min Range: -7.4654
Max Act: 7.4654. Min Act: -0.1700
Data Index: 5381524 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4654. Min Range: -7.4654
Max Act: 7.1841. Min Act: -0.1700
Data Index: 6122695 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4654. Min Range: -7.4654
Max Act: 7.1529. Min Act: -0.1700
Data Index: 576442 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4654. Min Range: -7.4654
Max Act: 7.1529. Min Act: -0.1700
Data Index: 2642883 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4654. Min Range: -7.4654
Max Act: 7.0279. Min Act: -0.1700
Data Index: 956387 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.9966. Min Act: -0.1700
Data Index: 6501317 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.9654. Min Act: -0.1700
Data Index: 5672141 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.9029. Min Act: -0.1700
Data Index: 7563000 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.9341. Min Act: -0.1700
Data Index: 7907898 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.9029. Min Act: -0.1700
Data Index: 5435891 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.9029. Min Act: -0.1700
Data Index: 6267548 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.7779. Min Act: -0.1700
Data Index: 3728842 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.7779. Min Act: -0.1700
Data Index: 1711707 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.7154. Min Act: -0.1700
Data Index: 7774039 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.6841. Min Act: -0.1700
Data Index: 4120420 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.7154. Min Act: -0.1700
Data Index: 7188408 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.6529. Min Act: -0.1700
Data Index: 2255813 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.6529. Min Act: -0.1700
Data Index: 3555295 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.6529. Min Act: -0.1700
Data Index: 5312240 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4654. Min Range: -7.4654
Max Act: 6.6529. Min Act: -0.1700
Data Index: 6170122 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19