Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4944 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0826. Min Range: -7.0826
Max Act: 7.0826. Min Act: -0.1700
Data Index: 7451485 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0826. Min Range: -7.0826
Max Act: 7.0514. Min Act: -0.1700
Data Index: 7289133 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.9576. Min Act: -0.1700
Data Index: 2935855 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.9264. Min Act: -0.1700
Data Index: 6036773 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.8639. Min Act: -0.1700
Data Index: 5416871 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7701. Min Act: -0.1700
Data Index: 5802001 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.8014. Min Act: -0.1700
Data Index: 4194063 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7701. Min Act: -0.1700
Data Index: 3870773 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7701. Min Act: -0.1700
Data Index: 6830405 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7389. Min Act: -0.1700
Data Index: 2718102 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7389. Min Act: -0.1700
Data Index: 3398814 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7389. Min Act: -0.1700
Data Index: 8120527 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7701. Min Act: -0.1700
Data Index: 380648 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7389. Min Act: -0.1700
Data Index: 6496334 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7076. Min Act: -0.1700
Data Index: 8470160 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7389. Min Act: -0.1700
Data Index: 5942359 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7389. Min Act: -0.1700
Data Index: 6857614 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7389. Min Act: -0.1700
Data Index: 256826 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.7076. Min Act: -0.1700
Data Index: 6418097 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0826. Min Range: -7.0826
Max Act: 6.6764. Min Act: -0.1700
Data Index: 8470159 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19