Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4135 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8032. Min Range: -10.8032
Max Act: 10.8032. Min Act: -0.1700
Data Index: 6113690 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8032. Min Range: -10.8032
Max Act: 10.4282. Min Act: -0.1700
Data Index: 8244740 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8032. Min Range: -10.8032
Max Act: 10.3657. Min Act: -0.1700
Data Index: 7325528 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8032. Min Range: -10.8032
Max Act: 10.1157. Min Act: -0.1700
Data Index: 986040 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8032. Min Range: -10.8032
Max Act: 10.1157. Min Act: -0.1700
Data Index: 2067400 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8032. Min Range: -10.8032
Max Act: 10.1157. Min Act: -0.1700
Data Index: 2439672 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8032. Min Range: -10.8032
Max Act: 10.0532. Min Act: -0.1700
Data Index: 7859258 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.9282. Min Act: -0.1700
Data Index: 5459808 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.9282. Min Act: -0.1700
Data Index: 8105364 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8657. Min Act: -0.1700
Data Index: 8364986 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8657. Min Act: -0.1700
Data Index: 3206855 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8657. Min Act: -0.1700
Data Index: 5589872 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8657. Min Act: -0.1697
Data Index: 7863325 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.9282. Min Act: -0.1700
Data Index: 6086740 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8657. Min Act: -0.1700
Data Index: 45841 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8032. Min Act: -0.1700
Data Index: 1045841 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8032. Min Act: -0.1700
Data Index: 8388767 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8032. Min Act: -0.1700
Data Index: 7832535 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.8032. Min Act: -0.1700
Data Index: 3682461 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8032. Min Range: -10.8032
Max Act: 9.6782. Min Act: -0.1700
Data Index: 6353473 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19