Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5068 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.2654. Min Act: -0.1700
Data Index: 2588414 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.1717. Min Act: -0.1700
Data Index: 21904 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.1717. Min Act: -0.1700
Data Index: 7180722 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.1404. Min Act: -0.1700
Data Index: 8149877 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.1404. Min Act: -0.1700
Data Index: 7664699 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.1092. Min Act: -0.1700
Data Index: 2381697 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.0779. Min Act: -0.1700
Data Index: 4284317 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.0466. Min Act: -0.1700
Data Index: 4320110 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.0466. Min Act: -0.1700
Data Index: 8250869 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.0154. Min Act: -0.1700
Data Index: 3137343 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.0154. Min Act: -0.1700
Data Index: 6858976 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.0154. Min Act: -0.1700
Data Index: 893234 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2654. Min Range: -4.2654
Max Act: 4.0154. Min Act: -0.1700
Data Index: 626608 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2654. Min Range: -4.2654
Max Act: 3.9529. Min Act: -0.1700
Data Index: 3414813 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2654. Min Range: -4.2654
Max Act: 3.9529. Min Act: -0.1700
Data Index: 8128200 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2654. Min Range: -4.2654
Max Act: 3.9216. Min Act: -0.1700
Data Index: 5946926 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2654. Min Range: -4.2654
Max Act: 3.9529. Min Act: -0.1700
Data Index: 2350941 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2654. Min Range: -4.2654
Max Act: 3.9216. Min Act: -0.1700
Data Index: 23918 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2654. Min Range: -4.2654
Max Act: 3.9216. Min Act: -0.1700
Data Index: 5315826 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2654. Min Range: -4.2654
Max Act: 3.9060. Min Act: -0.1700
Data Index: 6048882 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19