Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.6536. Min Act: -0.1700
Data Index: 7935296 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.6224. Min Act: -0.1700
Data Index: 8633621 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.5911. Min Act: -0.1700
Data Index: 8346378 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.5599. Min Act: -0.1700
Data Index: 5495585 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.4661. Min Act: -0.1700
Data Index: 3204876 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.4974. Min Act: -0.1700
Data Index: 2737940 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.4661. Min Act: -0.1700
Data Index: 2270983 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.4661. Min Act: -0.1700
Data Index: 5952720 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.4036. Min Act: -0.1700
Data Index: 1665625 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.4036. Min Act: -0.1700
Data Index: 33328 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.4036. Min Act: -0.1700
Data Index: 3395086 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.4036. Min Act: -0.1700
Data Index: 4122818 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.3724. Min Act: -0.1700
Data Index: 2910742 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.3724. Min Act: -0.1700
Data Index: 6230843 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.3724. Min Act: -0.1700
Data Index: 4863786 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.3724. Min Act: -0.1700
Data Index: 8479109 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.3724. Min Act: -0.1700
Data Index: 5413503 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.3724. Min Act: -0.1700
Data Index: 1712896 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.3724. Min Act: -0.1700
Data Index: 3516609 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6536. Min Range: -5.6536
Max Act: 5.3411. Min Act: -0.1700
Data Index: 5441238 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19