Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 441 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0327. Min Range: -7.0327
Max Act: 7.0327. Min Act: -0.1700
Data Index: 6837229 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9702. Min Act: -0.1700
Data Index: 1430099 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9702. Min Act: -0.1700
Data Index: 4621636 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9390. Min Act: -0.1700
Data Index: 6004735 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9390. Min Act: -0.1700
Data Index: 7889942 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9390. Min Act: -0.1700
Data Index: 6993679 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9390. Min Act: -0.1700
Data Index: 6975460 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9390. Min Act: -0.1700
Data Index: 3992712 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9390. Min Act: -0.1700
Data Index: 8774761 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 4046100 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 6220493 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 6826616 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 6159052 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 2701830 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 5381127 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 6146721 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 593489 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 5652132 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 2947567 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 8000552 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19