Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3327 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.9128. Min Act: -0.1700
Data Index: 6497452 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.2253. Min Act: -0.1700
Data Index: 3644849 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.1628. Min Act: -0.1700
Data Index: 6900756 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.1940. Min Act: -0.1700
Data Index: 3466644 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.0690. Min Act: -0.1700
Data Index: 1989242 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.0690. Min Act: -0.1700
Data Index: 5314321 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.0690. Min Act: -0.1700
Data Index: 3982736 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.9440. Min Act: -0.1700
Data Index: 1903418 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.8503. Min Act: -0.1700
Data Index: 6343951 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.8815. Min Act: -0.1700
Data Index: 5475947 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.8815. Min Act: -0.1700
Data Index: 1494749 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.8503. Min Act: -0.1700
Data Index: 2834469 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.8190. Min Act: -0.1700
Data Index: 4169851 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.8190. Min Act: -0.1700
Data Index: 5833711 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.7565. Min Act: -0.1700
Data Index: 8750166 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.7878. Min Act: -0.1700
Data Index: 5932661 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.7878. Min Act: -0.1700
Data Index: 7826136 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.7565. Min Act: -0.1700
Data Index: 3327010 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.7565. Min Act: -0.1700
Data Index: 749939 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9128. Min Range: -6.9128
Max Act: 5.7565. Min Act: -0.1700
Data Index: 6737965 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19