Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3609 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.8832. Min Act: -0.1700
Data Index: 7830719 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.6957. Min Act: -0.1700
Data Index: 27787 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.6957. Min Act: -0.1700
Data Index: 653872 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.6957. Min Act: -0.1700
Data Index: 4269789 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.6957. Min Act: -0.1700
Data Index: 821063 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.6332. Min Act: -0.1700
Data Index: 5369944 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.6332. Min Act: -0.1700
Data Index: 5174969 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.5707. Min Act: -0.1700
Data Index: 2507568 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.5707. Min Act: -0.1700
Data Index: 8318173 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.5707. Min Act: -0.1700
Data Index: 8816891 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.5707. Min Act: -0.1700
Data Index: 4151739 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.5082. Min Act: -0.1700
Data Index: 5221300 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.4457. Min Act: -0.1700
Data Index: 4415405 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.3832. Min Act: -0.1700
Data Index: 7649259 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.3832. Min Act: -0.1700
Data Index: 127988 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.3207. Min Act: -0.1700
Data Index: 7703443 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.3207. Min Act: -0.1700
Data Index: 752486 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.3207. Min Act: -0.1700
Data Index: 3767214 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.3832. Min Act: -0.1700
Data Index: 4396393 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8832. Min Range: -8.8832
Max Act: 8.2582. Min Act: -0.1700
Data Index: 7431837 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19