Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 514 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.9676. Min Act: -0.1700
Data Index: 3679007 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.9364. Min Act: -0.1700
Data Index: 2104250 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.9364. Min Act: -0.1700
Data Index: 4061279 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.8739. Min Act: -0.1700
Data Index: 5253107 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.8114. Min Act: -0.1700
Data Index: 8125025 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.8426. Min Act: -0.1700
Data Index: 4387353 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.8114. Min Act: -0.1700
Data Index: 927404 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.7801. Min Act: -0.1700
Data Index: 4600491 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.7489. Min Act: -0.1700
Data Index: 3677148 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.7176. Min Act: -0.1700
Data Index: 415448 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.7176. Min Act: -0.1700
Data Index: 4214659 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6864. Min Act: -0.1700
Data Index: 6460478 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 6990130 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6864. Min Act: -0.1700
Data Index: 5778886 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 2662092 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 7971955 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 4961423 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 4412705 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 581529 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9676. Min Range: -5.9676
Max Act: 5.6551. Min Act: -0.1700
Data Index: 2026746 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19