Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1634 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3059. Min Range: -8.3059
Max Act: 8.3059. Min Act: -0.1700
Data Index: 1713255 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3059. Min Range: -8.3059
Max Act: 8.2434. Min Act: -0.1700
Data Index: 8637446 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3059. Min Range: -8.3059
Max Act: 8.1809. Min Act: -0.1700
Data Index: 6723237 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3059. Min Range: -8.3059
Max Act: 8.1809. Min Act: -0.1700
Data Index: 8534619 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3059. Min Range: -8.3059
Max Act: 8.0559. Min Act: -0.1700
Data Index: 8370432 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.9934. Min Act: -0.1700
Data Index: 2671667 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.9934. Min Act: -0.1700
Data Index: 4745078 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.9309. Min Act: -0.1700
Data Index: 1329869 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.9309. Min Act: -0.1700
Data Index: 6904021 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.9309. Min Act: -0.1700
Data Index: 4896231 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.9309. Min Act: -0.1700
Data Index: 3220978 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.9309. Min Act: -0.1700
Data Index: 7394050 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.8684. Min Act: -0.1700
Data Index: 4239634 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.8684. Min Act: -0.1700
Data Index: 1845737 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.8684. Min Act: -0.1700
Data Index: 4574137 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.8371. Min Act: -0.1700
Data Index: 7950159 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.8371. Min Act: -0.1700
Data Index: 7794452 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.8371. Min Act: -0.1700
Data Index: 6356549 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.8059. Min Act: -0.1700
Data Index: 8439779 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3059. Min Range: -8.3059
Max Act: 7.8059. Min Act: -0.1700
Data Index: 2043402 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19