Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2386 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1236. Min Range: -5.1236
Max Act: 5.1236. Min Act: -0.1700
Data Index: 3510157 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.7173. Min Act: -0.1700
Data Index: 1996131 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.6861. Min Act: -0.1700
Data Index: 3740937 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.6861. Min Act: -0.1700
Data Index: 4634796 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.6548. Min Act: -0.1700
Data Index: 6431908 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.6548. Min Act: -0.1700
Data Index: 3985618 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.6236. Min Act: -0.1700
Data Index: 5081232 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.6236. Min Act: -0.1700
Data Index: 4511655 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.5611. Min Act: -0.1700
Data Index: 5100122 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4986. Min Act: -0.1700
Data Index: 4699804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4986. Min Act: -0.1700
Data Index: 4232385 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4361. Min Act: -0.1700
Data Index: 1721198 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4673. Min Act: -0.1700
Data Index: 4493349 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4361. Min Act: -0.1700
Data Index: 3255555 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4361. Min Act: -0.1700
Data Index: 190835 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4361. Min Act: -0.1700
Data Index: 1479929 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4361. Min Act: -0.1700
Data Index: 3816250 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4048. Min Act: -0.1700
Data Index: 648131 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.4048. Min Act: -0.1700
Data Index: 4003551 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.3736. Min Act: -0.1700
Data Index: 3306630 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19