Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6938. Min Range: -6.6938
Max Act: 6.6938. Min Act: -0.1700
Data Index: 6026678 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6938. Min Range: -6.6938
Max Act: 6.2563. Min Act: -0.1700
Data Index: 5552401 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6938. Min Range: -6.6938
Max Act: 6.1938. Min Act: -0.1700
Data Index: 4833384 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6938. Min Range: -6.6938
Max Act: 6.1001. Min Act: -0.1700
Data Index: 4045740 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6938. Min Range: -6.6938
Max Act: 6.1001. Min Act: -0.1700
Data Index: 5744610 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6938. Min Range: -6.6938
Max Act: 6.0063. Min Act: -0.1700
Data Index: 8206774 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.9751. Min Act: -0.1700
Data Index: 5134306 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.9751. Min Act: -0.1700
Data Index: 1662792 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.9751. Min Act: -0.1700
Data Index: 2300385 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.8813. Min Act: -0.1700
Data Index: 6465989 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.8501. Min Act: -0.1700
Data Index: 128113 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.8813. Min Act: -0.1700
Data Index: 7729695 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.8501. Min Act: -0.1700
Data Index: 6135449 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.8501. Min Act: -0.1700
Data Index: 3608610 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.8188. Min Act: -0.1700
Data Index: 3936307 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.8501. Min Act: -0.1700
Data Index: 109839 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.8188. Min Act: -0.1700
Data Index: 7502528 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.7876. Min Act: -0.1700
Data Index: 5828454 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.7876. Min Act: -0.1700
Data Index: 3495963 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6938. Min Range: -6.6938
Max Act: 5.7876. Min Act: -0.1700
Data Index: 6113758 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19