Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2130 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2797. Min Range: -6.2797
Max Act: 6.2797. Min Act: -0.1700
Data Index: 4383708 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2797. Min Range: -6.2797
Max Act: 6.1547. Min Act: -0.1700
Data Index: 3293770 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2797. Min Range: -6.2797
Max Act: 6.0922. Min Act: -0.1700
Data Index: 8735845 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2797. Min Range: -6.2797
Max Act: 6.0922. Min Act: -0.1700
Data Index: 1299022 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2797. Min Range: -6.2797
Max Act: 6.0922. Min Act: -0.1700
Data Index: 7563534 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2797. Min Range: -6.2797
Max Act: 6.0922. Min Act: -0.1700
Data Index: 5806952 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2797. Min Range: -6.2797
Max Act: 6.0297. Min Act: -0.1700
Data Index: 2641835 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.9984. Min Act: -0.1700
Data Index: 7934807 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.9984. Min Act: -0.1700
Data Index: 1537349 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.8734. Min Act: -0.1700
Data Index: 1636711 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.9047. Min Act: -0.1700
Data Index: 2283229 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.8734. Min Act: -0.1700
Data Index: 6060454 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.8422. Min Act: -0.1700
Data Index: 6815273 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.8422. Min Act: -0.1700
Data Index: 4784011 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.8109. Min Act: -0.1700
Data Index: 2402477 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.8109. Min Act: -0.1700
Data Index: 8258376 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.8109. Min Act: -0.1700
Data Index: 4316444 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.8109. Min Act: -0.1700
Data Index: 2905076 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.7484. Min Act: -0.1700
Data Index: 120832 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2797. Min Range: -6.2797
Max Act: 5.7797. Min Act: -0.1700
Data Index: 6025265 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19