Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4681 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.8001. Min Act: -0.1700
Data Index: 1106215 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.6438. Min Act: -0.1700
Data Index: 6761801 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.5501. Min Act: -0.1700
Data Index: 4831809 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.5813. Min Act: -0.1700
Data Index: 4324668 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.5501. Min Act: -0.1700
Data Index: 3467007 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.5501. Min Act: -0.1700
Data Index: 6058333 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.5813. Min Act: -0.1700
Data Index: 8035918 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.5501. Min Act: -0.1700
Data Index: 5589349 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4876. Min Act: -0.1700
Data Index: 2392470 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4563. Min Act: -0.1700
Data Index: 2674623 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4876. Min Act: -0.1700
Data Index: 1270365 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4876. Min Act: -0.1700
Data Index: 1398775 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4563. Min Act: -0.1700
Data Index: 6696076 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4563. Min Act: -0.1700
Data Index: 1591491 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4251. Min Act: -0.1700
Data Index: 6605109 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4251. Min Act: -0.1700
Data Index: 2023860 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.4251. Min Act: -0.1700
Data Index: 5588899 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.3938. Min Act: -0.1700
Data Index: 2826960 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.3626. Min Act: -0.1700
Data Index: 2382143 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8001. Min Range: -5.8001
Max Act: 5.3626. Min Act: -0.1700
Data Index: 4440947 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19