Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.7771. Min Act: -0.1700
Data Index: 1212364 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.4021. Min Act: -0.1700
Data Index: 5347938 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.4646. Min Act: -0.1700
Data Index: 5361954 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.3396. Min Act: -0.1700
Data Index: 5513428 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.3396. Min Act: -0.1700
Data Index: 4119897 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.2771. Min Act: -0.1700
Data Index: 5151749 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.2771. Min Act: -0.1700
Data Index: 7980977 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.2771. Min Act: -0.1700
Data Index: 3717507 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.2146. Min Act: -0.1700
Data Index: 6167346 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.1521. Min Act: -0.1700
Data Index: 3347051 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.2146. Min Act: -0.1700
Data Index: 5709611 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.1521. Min Act: -0.1700
Data Index: 7858578 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.1521. Min Act: -0.1700
Data Index: 4231767 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.0896. Min Act: -0.1700
Data Index: 126779 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.0896. Min Act: -0.1700
Data Index: 578974 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.0896. Min Act: -0.1700
Data Index: 625940 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.0896. Min Act: -0.1700
Data Index: 670148 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.0896. Min Act: -0.1700
Data Index: 3626571 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.0896. Min Act: -0.1700
Data Index: 4343562 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7771. Min Range: -8.7771
Max Act: 8.0896. Min Act: -0.1700
Data Index: 5472857 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19