Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5470 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4784. Min Range: -8.4784
Max Act: 8.4784. Min Act: -0.1700
Data Index: 2328307 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4784. Min Range: -8.4784
Max Act: 8.1034. Min Act: -0.1700
Data Index: 5318813 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.9784. Min Act: -0.1700
Data Index: 1591227 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4784. Min Range: -8.4784
Max Act: 8.0096. Min Act: -0.1700
Data Index: 122383 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.9159. Min Act: -0.1700
Data Index: 5643695 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.9159. Min Act: -0.1700
Data Index: 6740784 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8846. Min Act: -0.1700
Data Index: 4342306 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8534. Min Act: -0.1700
Data Index: 2866486 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8221. Min Act: -0.1700
Data Index: 2950930 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8846. Min Act: -0.1700
Data Index: 7211046 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8534. Min Act: -0.1700
Data Index: 1921080 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8534. Min Act: -0.1700
Data Index: 1741765 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8534. Min Act: -0.1700
Data Index: 1016437 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8221. Min Act: -0.1700
Data Index: 115117 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8534. Min Act: -0.1700
Data Index: 1165270 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8534. Min Act: -0.1700
Data Index: 1181662 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8221. Min Act: -0.1700
Data Index: 1016436 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.8534. Min Act: -0.1700
Data Index: 1644514 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.7909. Min Act: -0.1700
Data Index: 440226 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4784. Min Range: -8.4784
Max Act: 7.7909. Min Act: -0.1700
Data Index: 4919456 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19