Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2653 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0839. Min Range: -8.0839
Max Act: 8.0839. Min Act: -0.1700
Data Index: 4464687 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.9589. Min Act: -0.1700
Data Index: 3500217 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.9902. Min Act: -0.1700
Data Index: 2602032 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.8964. Min Act: -0.1700
Data Index: 7594978 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.8964. Min Act: -0.1700
Data Index: 8374805 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.8964. Min Act: -0.1700
Data Index: 7102376 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.8964. Min Act: -0.1700
Data Index: 1064047 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.8652. Min Act: -0.1700
Data Index: 1463991 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.8652. Min Act: -0.1700
Data Index: 1831650 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.8652. Min Act: -0.1700
Data Index: 4110680 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.8027. Min Act: -0.1700
Data Index: 2765470 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.7714. Min Act: -0.1700
Data Index: 5073538 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.7714. Min Act: -0.1700
Data Index: 1229967 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.7402. Min Act: -0.1700
Data Index: 2942069 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.7402. Min Act: -0.1700
Data Index: 2296441 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.7089. Min Act: -0.1700
Data Index: 7880669 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.7089. Min Act: -0.1700
Data Index: 8790745 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.6777. Min Act: -0.1700
Data Index: 6592004 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.7089. Min Act: -0.1700
Data Index: 5139882 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0839. Min Range: -8.0839
Max Act: 7.7089. Min Act: -0.1700
Data Index: 3420735 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19