Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3862 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.9204. Min Act: -0.1700
Data Index: 1887055 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.8579. Min Act: -0.1700
Data Index: 1035871 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.8267. Min Act: -0.1700
Data Index: 1603633 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.8267. Min Act: -0.1700
Data Index: 6560728 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.7642. Min Act: -0.1700
Data Index: 92392 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.7329. Min Act: -0.1700
Data Index: 8176994 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.7329. Min Act: -0.1700
Data Index: 856589 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.7017. Min Act: -0.1700
Data Index: 4702778 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.6704. Min Act: -0.1700
Data Index: 5977462 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.6704. Min Act: -0.1700
Data Index: 4908738 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.6704. Min Act: -0.1700
Data Index: 92391 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.6392. Min Act: -0.1700
Data Index: 6575680 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.6392. Min Act: -0.1700
Data Index: 1624375 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.6079. Min Act: -0.1700
Data Index: 3416510 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.5767. Min Act: -0.1700
Data Index: 5878716 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.5767. Min Act: -0.1700
Data Index: 8071608 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.5767. Min Act: -0.1700
Data Index: 1463988 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.5454. Min Act: -0.1700
Data Index: 5705886 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.5454. Min Act: -0.1700
Data Index: 2128178 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9204. Min Range: -5.9204
Max Act: 5.5454. Min Act: -0.1700
Data Index: 7142599 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19