Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.7292. Min Act: -0.1700
Data Index: 8037886 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.6667. Min Act: -0.1700
Data Index: 5204019 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.6042. Min Act: -0.1700
Data Index: 5550557 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.6042. Min Act: -0.1700
Data Index: 35767 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5730. Min Act: -0.1700
Data Index: 2611133 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5730. Min Act: -0.1700
Data Index: 5643157 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5417. Min Act: -0.1700
Data Index: 2061912 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5417. Min Act: -0.1700
Data Index: 5328137 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5417. Min Act: -0.1700
Data Index: 4613576 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5417. Min Act: -0.1700
Data Index: 6127478 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5105. Min Act: -0.1700
Data Index: 4519663 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5417. Min Act: -0.1700
Data Index: 3695749 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5105. Min Act: -0.1700
Data Index: 287367 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.4792. Min Act: -0.1700
Data Index: 7916512 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.4792. Min Act: -0.1700
Data Index: 6127477 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5105. Min Act: -0.1700
Data Index: 884674 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5105. Min Act: -0.1700
Data Index: 7593044 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5417. Min Act: -0.1700
Data Index: 1606396 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.5105. Min Act: -0.1700
Data Index: 4775053 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7292. Min Range: -6.7292
Max Act: 6.4792. Min Act: -0.1700
Data Index: 4565190 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19