Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.5563. Min Act: -0.1700
Data Index: 3780081 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.4938. Min Act: -0.1700
Data Index: 6306693 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.4626. Min Act: -0.1700
Data Index: 3134781 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.3688. Min Act: -0.1700
Data Index: 8326869 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.3063. Min Act: -0.1700
Data Index: 6328443 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.3063. Min Act: -0.1700
Data Index: 8743070 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.2438. Min Act: -0.1700
Data Index: 2301687 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.2126. Min Act: -0.1700
Data Index: 7653328 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.2126. Min Act: -0.1700
Data Index: 5076253 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.1813. Min Act: -0.1700
Data Index: 7653329 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.1813. Min Act: -0.1700
Data Index: 8618808 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.1188. Min Act: -0.1700
Data Index: 4625234 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.1501. Min Act: -0.1700
Data Index: 7280695 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.0876. Min Act: -0.1700
Data Index: 6498065 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.0876. Min Act: -0.1700
Data Index: 7196945 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.1188. Min Act: -0.1700
Data Index: 4690442 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.0563. Min Act: -0.1700
Data Index: 2302883 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.0563. Min Act: -0.1700
Data Index: 1617530 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.0251. Min Act: -0.1700
Data Index: 6879126 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5563. Min Range: -6.5563
Max Act: 6.0251. Min Act: -0.1700
Data Index: 1119273 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19