Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6333 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3119. Min Range: -8.3119
Max Act: 8.3119. Min Act: -0.1700
Data Index: 3623090 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.9369. Min Act: -0.1700
Data Index: 4550486 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.8744. Min Act: -0.1700
Data Index: 3609732 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.8744. Min Act: -0.1700
Data Index: 3967268 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.8119. Min Act: -0.1700
Data Index: 2314108 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.8119. Min Act: -0.1700
Data Index: 6010009 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.8119. Min Act: -0.1700
Data Index: 6013757 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.7494. Min Act: -0.1700
Data Index: 7739059 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.6244. Min Act: -0.1700
Data Index: 2430268 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.6869. Min Act: -0.1700
Data Index: 634751 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.6244. Min Act: -0.1700
Data Index: 5814324 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.6244. Min Act: -0.1700
Data Index: 1749144 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.5619. Min Act: -0.1700
Data Index: 321342 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.5619. Min Act: -0.1700
Data Index: 3918871 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.5619. Min Act: -0.1700
Data Index: 1219624 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.5619. Min Act: -0.1700
Data Index: 7032483 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.5619. Min Act: -0.1700
Data Index: 4690869 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.5619. Min Act: -0.1700
Data Index: 5442880 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.5619. Min Act: -0.1700
Data Index: 4961809 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3119. Min Range: -8.3119
Max Act: 7.4994. Min Act: -0.1700
Data Index: 776470 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19