Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.6441. Min Act: -0.1700
Data Index: 2660158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.6441. Min Act: -0.1700
Data Index: 8729980 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.6441. Min Act: -0.1700
Data Index: 6076984 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.6128. Min Act: -0.1700
Data Index: 1208140 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5816. Min Act: -0.1700
Data Index: 4006849 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5503. Min Act: -0.1700
Data Index: 863142 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5816. Min Act: -0.1700
Data Index: 2275386 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5503. Min Act: -0.1700
Data Index: 5682553 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5191. Min Act: -0.1700
Data Index: 4236555 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5191. Min Act: -0.1700
Data Index: 6852464 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5191. Min Act: -0.1700
Data Index: 5492486 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5191. Min Act: -0.1700
Data Index: 3133321 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5191. Min Act: -0.1700
Data Index: 6886907 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.4878. Min Act: -0.1700
Data Index: 6792126 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.4566. Min Act: -0.1700
Data Index: 89732 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.4878. Min Act: -0.1700
Data Index: 2238314 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.5191. Min Act: -0.1700
Data Index: 4159010 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.4566. Min Act: -0.1700
Data Index: 1978534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.4566. Min Act: -0.1700
Data Index: 5527900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6441. Min Range: -5.6441
Max Act: 5.4566. Min Act: -0.1700
Data Index: 3387067 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19