Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.5053. Min Act: -0.1700
Data Index: 3106476 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2553. Min Act: -0.1700
Data Index: 6312740 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2553. Min Act: -0.1700
Data Index: 6842043 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2553. Min Act: -0.1700
Data Index: 213481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.1928. Min Act: -0.1700
Data Index: 2864565 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.1928. Min Act: -0.1700
Data Index: 5215576 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.1615. Min Act: -0.1700
Data Index: 3206853 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.1303. Min Act: -0.1700
Data Index: 6918907 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0990. Min Act: -0.1700
Data Index: 2951601 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0990. Min Act: -0.1700
Data Index: 2783844 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0990. Min Act: -0.1700
Data Index: 5397842 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0990. Min Act: -0.1700
Data Index: 4039643 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3173468 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0678. Min Act: -0.1700
Data Index: 5071330 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0678. Min Act: -0.1700
Data Index: 3657668 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0678. Min Act: -0.1700
Data Index: 1000157 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0678. Min Act: -0.1700
Data Index: 1059668 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0678. Min Act: -0.1700
Data Index: 6726967 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0678. Min Act: -0.1700
Data Index: 8122877 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0678. Min Act: -0.1700
Data Index: 8431563 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19