Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.8870. Min Act: -0.1700
Data Index: 7894604 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.8245. Min Act: -0.1700
Data Index: 3972565 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.8245. Min Act: -0.1700
Data Index: 5991471 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.8245. Min Act: -0.1700
Data Index: 6914050 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.6995. Min Act: -0.1700
Data Index: 3316832 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.6370. Min Act: -0.1700
Data Index: 2641958 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.4495. Min Act: -0.1700
Data Index: 4909203 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.3870. Min Act: -0.1700
Data Index: 978688 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.3870. Min Act: -0.1700
Data Index: 2738396 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.4495. Min Act: -0.1700
Data Index: 4751337 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.3245. Min Act: -0.1700
Data Index: 1440001 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.3245. Min Act: -0.1700
Data Index: 447446 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.3245. Min Act: -0.1700
Data Index: 6806667 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.3245. Min Act: -0.1700
Data Index: 2229509 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.2620. Min Act: -0.1700
Data Index: 5144693 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.2620. Min Act: -0.1700
Data Index: 2502559 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.2620. Min Act: -0.1700
Data Index: 8300313 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.1995. Min Act: -0.1700
Data Index: 102492 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.1995. Min Act: -0.1700
Data Index: 1748452 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8870. Min Range: -8.8870
Max Act: 8.2620. Min Act: -0.1700
Data Index: 5394964 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19