Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3388 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2087. Min Range: -6.2087
Max Act: 6.2087. Min Act: -0.1700
Data Index: 5868744 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2087. Min Range: -6.2087
Max Act: 6.0212. Min Act: -0.1700
Data Index: 4583746 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.9899. Min Act: -0.1700
Data Index: 7933401 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.9587. Min Act: -0.1700
Data Index: 5985547 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.9587. Min Act: -0.1700
Data Index: 5095732 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.9274. Min Act: -0.1700
Data Index: 3861868 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.8962. Min Act: -0.1700
Data Index: 6304149 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.8649. Min Act: -0.1700
Data Index: 2426178 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.8024. Min Act: -0.1700
Data Index: 6831847 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7399. Min Act: -0.1700
Data Index: 2293122 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7712. Min Act: -0.1700
Data Index: 2022510 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7399. Min Act: -0.1700
Data Index: 4092988 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7399. Min Act: -0.1700
Data Index: 3937910 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7399. Min Act: -0.1700
Data Index: 970295 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 7257393 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 6038705 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 4240764 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 1753690 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 386700 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2087. Min Range: -6.2087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 4320052 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19