Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.9709. Min Act: -0.1700
Data Index: 5985483 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.9396. Min Act: -0.1700
Data Index: 4172106 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.9396. Min Act: -0.1700
Data Index: 8689991 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.9396. Min Act: -0.1700
Data Index: 3660764 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8771. Min Act: -0.1700
Data Index: 4433258 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8458. Min Act: -0.1700
Data Index: 3660762 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8771. Min Act: -0.1700
Data Index: 8689992 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8145. Min Act: -0.1700
Data Index: 8749272 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7989. Min Act: -0.1700
Data Index: 2412384 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8145. Min Act: -0.1700
Data Index: 7771080 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7832. Min Act: -0.1700
Data Index: 2094810 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7832. Min Act: -0.1700
Data Index: 8107057 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7676. Min Act: -0.1700
Data Index: 5212300 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7520. Min Act: -0.1700
Data Index: 6632350 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7363. Min Act: -0.1700
Data Index: 6188692 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7520. Min Act: -0.1700
Data Index: 8121807 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7050. Min Act: -0.1700
Data Index: 838897 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7207. Min Act: -0.1700
Data Index: 1320539 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7207. Min Act: -0.1700
Data Index: 1009990 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7363. Min Act: -0.1700
Data Index: 5939995 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19