Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.3699. Min Act: -0.1700
Data Index: 5899206 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.3387. Min Act: -0.1700
Data Index: 5440584 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.3699. Min Act: -0.1700
Data Index: 1984062 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.2762. Min Act: -0.1700
Data Index: 1677785 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.2449. Min Act: -0.1700
Data Index: 244871 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.2137. Min Act: -0.1700
Data Index: 78921 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.1199. Min Act: -0.1700
Data Index: 8608909 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.1199. Min Act: -0.1700
Data Index: 8297567 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.0887. Min Act: -0.1700
Data Index: 7234271 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.0574. Min Act: -0.1700
Data Index: 8526080 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.0574. Min Act: -0.1700
Data Index: 7915571 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3699. Min Range: -6.3699
Max Act: 6.0574. Min Act: -0.1700
Data Index: 6367435 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3699. Min Range: -6.3699
Max Act: 5.9949. Min Act: -0.1700
Data Index: 2734655 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3699. Min Range: -6.3699
Max Act: 5.9637. Min Act: -0.1700
Data Index: 8760636 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3699. Min Range: -6.3699
Max Act: 5.9949. Min Act: -0.1700
Data Index: 7872832 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3699. Min Range: -6.3699
Max Act: 5.9637. Min Act: -0.1700
Data Index: 802796 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3699. Min Range: -6.3699
Max Act: 5.9637. Min Act: -0.1700
Data Index: 2874340 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3699. Min Range: -6.3699
Max Act: 5.9637. Min Act: -0.1700
Data Index: 1725227 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3699. Min Range: -6.3699
Max Act: 5.9324. Min Act: -0.1700
Data Index: 4898096 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3699. Min Range: -6.3699
Max Act: 5.9324. Min Act: -0.1700
Data Index: 3098688 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19