Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.7917. Min Act: -0.1700
Data Index: 2479787 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.7604. Min Act: -0.1700
Data Index: 4346228 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.7292. Min Act: -0.1700
Data Index: 2396748 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6667. Min Act: -0.1700
Data Index: 2448826 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6979. Min Act: -0.1700
Data Index: 7509537 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6667. Min Act: -0.1700
Data Index: 5266446 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6667. Min Act: -0.1700
Data Index: 2457440 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6354. Min Act: -0.1700
Data Index: 1664286 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6354. Min Act: -0.1700
Data Index: 7610347 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6042. Min Act: -0.1700
Data Index: 8669069 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.5729. Min Act: -0.1700
Data Index: 4713750 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6042. Min Act: -0.1700
Data Index: 4501962 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6042. Min Act: -0.1700
Data Index: 119481 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6354. Min Act: -0.1700
Data Index: 8274223 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6042. Min Act: -0.1700
Data Index: 4278074 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.5729. Min Act: -0.1700
Data Index: 3510000 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.5729. Min Act: -0.1700
Data Index: 3921300 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.5729. Min Act: -0.1700
Data Index: 4278075 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.5729. Min Act: -0.1700
Data Index: 4629973 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7917. Min Range: -6.7917
Max Act: 6.6042. Min Act: -0.1700
Data Index: 7334718 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19