Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.1401. Min Act: -0.1700
Data Index: 4876553 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.1713. Min Act: -0.1700
Data Index: 7797273 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.1401. Min Act: -0.1700
Data Index: 2796062 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.1088. Min Act: -0.1700
Data Index: 8006477 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.1088. Min Act: -0.1700
Data Index: 585738 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.1088. Min Act: -0.1700
Data Index: 8024970 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.0776. Min Act: -0.1700
Data Index: 8668851 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.0776. Min Act: -0.1700
Data Index: 2563704 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.0463. Min Act: -0.1700
Data Index: 8633424 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.0151. Min Act: -0.1700
Data Index: 7627405 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1713. Min Range: -5.1713
Max Act: 5.0151. Min Act: -0.1700
Data Index: 1535240 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9838. Min Act: -0.1700
Data Index: 1234461 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9838. Min Act: -0.1700
Data Index: 5693508 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9838. Min Act: -0.1700
Data Index: 654762 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9838. Min Act: -0.1700
Data Index: 6336166 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9838. Min Act: -0.1700
Data Index: 1532312 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9526. Min Act: -0.1700
Data Index: 8403333 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9526. Min Act: -0.1700
Data Index: 2493810 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9213. Min Act: -0.1700
Data Index: 585739 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1713. Min Range: -5.1713
Max Act: 4.9213. Min Act: -0.1700
Data Index: 6403891 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19