Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.2877. Min Act: -0.1700
Data Index: 1664632 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.2565. Min Act: -0.1700
Data Index: 3008328 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.1940. Min Act: -0.1700
Data Index: 4773122 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.2252. Min Act: -0.1700
Data Index: 2104885 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.1627. Min Act: -0.1700
Data Index: 1549493 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.1627. Min Act: -0.1700
Data Index: 6683312 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.1315. Min Act: -0.1700
Data Index: 7016619 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.1002. Min Act: -0.1700
Data Index: 5575639 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.0690. Min Act: -0.1700
Data Index: 1766244 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.0690. Min Act: -0.1700
Data Index: 473892 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.0377. Min Act: -0.1700
Data Index: 1780207 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.0377. Min Act: -0.1700
Data Index: 3406789 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4104526 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.0065. Min Act: -0.1700
Data Index: 2154843 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.0065. Min Act: -0.1700
Data Index: 476560 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2877. Min Range: -5.2877
Max Act: 5.0065. Min Act: -0.1700
Data Index: 8188646 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2877. Min Range: -5.2877
Max Act: 4.9752. Min Act: -0.1700
Data Index: 8239530 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2877. Min Range: -5.2877
Max Act: 4.9752. Min Act: -0.1700
Data Index: 4843398 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2877. Min Range: -5.2877
Max Act: 4.9752. Min Act: -0.1700
Data Index: 4738129 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2877. Min Range: -5.2877
Max Act: 4.9752. Min Act: -0.1700
Data Index: 1481809 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19