Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2738 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1735. Min Range: -7.1735
Max Act: 7.1735. Min Act: -0.1700
Data Index: 3182169 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1735. Min Range: -7.1735
Max Act: 7.0485. Min Act: -0.1700
Data Index: 2354035 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.9860. Min Act: -0.1700
Data Index: 7060448 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.9860. Min Act: -0.1700
Data Index: 427567 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.8922. Min Act: -0.1700
Data Index: 3785281 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.8922. Min Act: -0.1700
Data Index: 6441171 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.8610. Min Act: -0.1700
Data Index: 1839005 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7985. Min Act: -0.1700
Data Index: 481886 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7360. Min Act: -0.1700
Data Index: 959887 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7672. Min Act: -0.1700
Data Index: 3499431 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7672. Min Act: -0.1700
Data Index: 2312841 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7672. Min Act: -0.1700
Data Index: 1725126 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7360. Min Act: -0.1700
Data Index: 7550297 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7360. Min Act: -0.1700
Data Index: 4628382 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7047. Min Act: -0.1700
Data Index: 410629 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7047. Min Act: -0.1700
Data Index: 3012807 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7047. Min Act: -0.1700
Data Index: 6823103 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7047. Min Act: -0.1700
Data Index: 8250496 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6735. Min Act: -0.1700
Data Index: 4202788 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6422. Min Act: -0.1700
Data Index: 1871723 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19