Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0429. Min Range: -8.0429
Max Act: 8.0429. Min Act: -0.1700
Data Index: 54049 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0429. Min Range: -8.0429
Max Act: 7.1992. Min Act: -0.1700
Data Index: 4516000 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0429. Min Range: -8.0429
Max Act: 7.2304. Min Act: -0.1700
Data Index: 3509787 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0429. Min Range: -8.0429
Max Act: 7.0429. Min Act: -0.1700
Data Index: 4339003 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0429. Min Range: -8.0429
Max Act: 7.0117. Min Act: -0.1700
Data Index: 3155891 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0429. Min Range: -8.0429
Max Act: 7.0117. Min Act: -0.1700
Data Index: 5367903 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0429. Min Range: -8.0429
Max Act: 7.0117. Min Act: -0.1700
Data Index: 2342427 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9804. Min Act: -0.1700
Data Index: 4221009 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0429. Min Range: -8.0429
Max Act: 7.0117. Min Act: -0.1700
Data Index: 8707851 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9804. Min Act: -0.1700
Data Index: 1855871 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9804. Min Act: -0.1700
Data Index: 2915573 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9804. Min Act: -0.1700
Data Index: 107148 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9492. Min Act: -0.1700
Data Index: 7676 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9492. Min Act: -0.1700
Data Index: 1604319 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9179. Min Act: -0.1700
Data Index: 5655205 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9179. Min Act: -0.1700
Data Index: 3485100 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9179. Min Act: -0.1700
Data Index: 3646336 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.9179. Min Act: -0.1700
Data Index: 917721 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.8867. Min Act: -0.1700
Data Index: 5187734 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0429. Min Range: -8.0429
Max Act: 6.8867. Min Act: -0.1700
Data Index: 6055464 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19