Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5951 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.5949. Min Act: -0.1700
Data Index: 982640 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.5637. Min Act: -0.1700
Data Index: 4525469 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.5012. Min Act: -0.1700
Data Index: 2168791 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.5324. Min Act: -0.1700
Data Index: 1460723 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.5012. Min Act: -0.1700
Data Index: 6891687 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4387. Min Act: -0.1700
Data Index: 1754325 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4699. Min Act: -0.1700
Data Index: 309079 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4699. Min Act: -0.1700
Data Index: 5324831 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4387. Min Act: -0.1700
Data Index: 3409506 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4387. Min Act: -0.1700
Data Index: 7877462 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4387. Min Act: -0.1700
Data Index: 5442192 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4387. Min Act: -0.1700
Data Index: 3356957 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4387. Min Act: -0.1700
Data Index: 2303065 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4074. Min Act: -0.1700
Data Index: 8584752 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.3762. Min Act: -0.1700
Data Index: 7796599 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4074. Min Act: -0.1700
Data Index: 8181340 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4074. Min Act: -0.1700
Data Index: 3419852 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.4074. Min Act: -0.1700
Data Index: 3011506 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.3762. Min Act: -0.1700
Data Index: 7906639 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5949. Min Range: -4.5949
Max Act: 4.3762. Min Act: -0.1700
Data Index: 787787 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19