Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3025. Min Range: -6.3025
Max Act: 6.3025. Min Act: -0.1700
Data Index: 1970428 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3025. Min Range: -6.3025
Max Act: 6.2400. Min Act: -0.1700
Data Index: 7356761 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.9900. Min Act: -0.1700
Data Index: 6406690 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.9900. Min Act: -0.1700
Data Index: 430886 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.8963. Min Act: -0.1700
Data Index: 58407 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.9275. Min Act: -0.1700
Data Index: 5173263 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.9275. Min Act: -0.1700
Data Index: 6516316 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.8650. Min Act: -0.1700
Data Index: 5168134 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.8650. Min Act: -0.1700
Data Index: 3415254 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.8338. Min Act: -0.1700
Data Index: 8000439 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.8338. Min Act: -0.1700
Data Index: 3586235 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.8025. Min Act: -0.1700
Data Index: 3302795 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.7713. Min Act: -0.1700
Data Index: 3529945 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.7400. Min Act: -0.1700
Data Index: 373373 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.7713. Min Act: -0.1700
Data Index: 871519 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.7088. Min Act: -0.1700
Data Index: 2610949 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.7400. Min Act: -0.1700
Data Index: 6857242 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.7088. Min Act: -0.1700
Data Index: 8065349 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.7088. Min Act: -0.1700
Data Index: 7421606 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3025. Min Range: -6.3025
Max Act: 5.7088. Min Act: -0.1700
Data Index: 2844563 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19