Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4428 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.9094. Min Act: -0.1700
Data Index: 3935393 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.8157. Min Act: -0.1700
Data Index: 4954528 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.7844. Min Act: -0.1700
Data Index: 2436749 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.6594. Min Act: -0.1700
Data Index: 5587277 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.6282. Min Act: -0.1700
Data Index: 3455498 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.5344. Min Act: -0.1700
Data Index: 7808148 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.5657. Min Act: -0.1700
Data Index: 4536320 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.5032. Min Act: -0.1700
Data Index: 8387215 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.5032. Min Act: -0.1700
Data Index: 8665977 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.4407. Min Act: -0.1700
Data Index: 6167434 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.4407. Min Act: -0.1700
Data Index: 5676619 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.4094. Min Act: -0.1700
Data Index: 2071860 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.4407. Min Act: -0.1700
Data Index: 6801641 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.3782. Min Act: -0.1700
Data Index: 6062469 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.3782. Min Act: -0.1700
Data Index: 4603567 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.3469. Min Act: -0.1700
Data Index: 8778957 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.3469. Min Act: -0.1700
Data Index: 355019 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.3469. Min Act: -0.1700
Data Index: 3354904 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.3157. Min Act: -0.1700
Data Index: 464938 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9094. Min Range: -6.9094
Max Act: 6.2844. Min Act: -0.1700
Data Index: 8310883 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19