Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.4035. Min Act: -0.1700
Data Index: 6383661 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.3098. Min Act: -0.1700
Data Index: 7205340 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.2785. Min Act: -0.1700
Data Index: 6436551 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.2473. Min Act: -0.1700
Data Index: 6316492 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.2473. Min Act: -0.1700
Data Index: 4878668 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.1848. Min Act: -0.1700
Data Index: 7501514 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.1535. Min Act: -0.1700
Data Index: 8045382 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.1223. Min Act: -0.1700
Data Index: 5215926 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.0910. Min Act: -0.1700
Data Index: 5174133 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.0598. Min Act: -0.1700
Data Index: 968293 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.0598. Min Act: -0.1700
Data Index: 4606879 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.0285. Min Act: -0.1700
Data Index: 1904678 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.0285. Min Act: -0.1700
Data Index: 3300722 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.0285. Min Act: -0.1700
Data Index: 2933090 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4035. Min Range: -5.4035
Max Act: 5.0285. Min Act: -0.1700
Data Index: 1315885 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4035. Min Range: -5.4035
Max Act: 4.9973. Min Act: -0.1700
Data Index: 2763837 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4035. Min Range: -5.4035
Max Act: 4.9973. Min Act: -0.1700
Data Index: 2198540 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4035. Min Range: -5.4035
Max Act: 4.9973. Min Act: -0.1700
Data Index: 7680646 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4035. Min Range: -5.4035
Max Act: 4.9660. Min Act: -0.1700
Data Index: 6713196 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4035. Min Range: -5.4035
Max Act: 4.9660. Min Act: -0.1700
Data Index: 2245669 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19