Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 851 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4329. Min Range: -5.4329
Max Act: 5.4329. Min Act: -0.1700
Data Index: 513930 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4329. Min Range: -5.4329
Max Act: 5.3079. Min Act: -0.1700
Data Index: 5145161 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4329. Min Range: -5.4329
Max Act: 5.1829. Min Act: -0.1700
Data Index: 7325228 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4329. Min Range: -5.4329
Max Act: 5.0892. Min Act: -0.1700
Data Index: 7221076 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4329. Min Range: -5.4329
Max Act: 5.0579. Min Act: -0.1700
Data Index: 7139534 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4329. Min Range: -5.4329
Max Act: 5.0267. Min Act: -0.1700
Data Index: 4977305 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4329. Min Range: -5.4329
Max Act: 5.0267. Min Act: -0.1700
Data Index: 5084769 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9954. Min Act: -0.1700
Data Index: 3710973 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9954. Min Act: -0.1700
Data Index: 7046397 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9954. Min Act: -0.1700
Data Index: 534591 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9954. Min Act: -0.1700
Data Index: 3471207 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9642. Min Act: -0.1700
Data Index: 2794956 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9642. Min Act: -0.1700
Data Index: 2269161 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9642. Min Act: -0.1700
Data Index: 7295826 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9642. Min Act: -0.1700
Data Index: 8420654 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9954. Min Act: -0.1700
Data Index: 4549190 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9329. Min Act: -0.1700
Data Index: 1716039 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9329. Min Act: -0.1700
Data Index: 2901908 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.8704. Min Act: -0.1700
Data Index: 2522302 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4329. Min Range: -5.4329
Max Act: 4.9017. Min Act: -0.1700
Data Index: 8053033 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19