Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5278 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.5251. Min Act: -0.1700
Data Index: 4173504 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.2751. Min Act: -0.1700
Data Index: 6716178 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.2126. Min Act: -0.1700
Data Index: 2571690 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.2126. Min Act: -0.1700
Data Index: 3001414 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.2126. Min Act: -0.1700
Data Index: 4543188 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.1501. Min Act: -0.1700
Data Index: 3877295 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.1501. Min Act: -0.1700
Data Index: 3001412 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.1501. Min Act: -0.1700
Data Index: 2571689 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5251. Min Range: -9.5251
Max Act: 9.0251. Min Act: -0.1700
Data Index: 1670109 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.9626. Min Act: -0.1700
Data Index: 670083 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.9001. Min Act: -0.1700
Data Index: 670082 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.9001. Min Act: -0.1700
Data Index: 4543189 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.9001. Min Act: -0.1700
Data Index: 8653850 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.8376. Min Act: -0.1700
Data Index: 4660499 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.8376. Min Act: -0.1700
Data Index: 4615380 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.7751. Min Act: -0.1700
Data Index: 6947883 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.7751. Min Act: -0.1700
Data Index: 3001413 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.7751. Min Act: -0.1700
Data Index: 6105065 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.7126. Min Act: -0.1700
Data Index: 4660498 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5251. Min Range: -9.5251
Max Act: 8.7126. Min Act: -0.1700
Data Index: 4724151 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19