Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.1627. Min Act: -0.1700
Data Index: 1918848 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.1627. Min Act: -0.1700
Data Index: 8320887 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.1002. Min Act: -0.1700
Data Index: 8782354 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.1002. Min Act: -0.1700
Data Index: 8569014 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.1002. Min Act: -0.1700
Data Index: 1896393 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.1002. Min Act: -0.1700
Data Index: 3788368 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0690. Min Act: -0.1700
Data Index: 8320524 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0690. Min Act: -0.1700
Data Index: 4604162 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0690. Min Act: -0.1700
Data Index: 8556972 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0690. Min Act: -0.1700
Data Index: 1003860 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0377. Min Act: -0.1700
Data Index: 4968592 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0690. Min Act: -0.1700
Data Index: 6775095 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0377. Min Act: -0.1700
Data Index: 2221448 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0377. Min Act: -0.1700
Data Index: 3959797 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0377. Min Act: -0.1700
Data Index: 6126195 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0377. Min Act: -0.1700
Data Index: 6557122 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4302348 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0065. Min Act: -0.1700
Data Index: 1618507 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1627. Min Range: -5.1627
Max Act: 4.9752. Min Act: -0.1700
Data Index: 5941443 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1627. Min Range: -5.1627
Max Act: 5.0065. Min Act: -0.1700
Data Index: 799770 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19