Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6353 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.1728. Min Act: -0.1700
Data Index: 3053405 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.1728. Min Act: -0.1700
Data Index: 6935844 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.1728. Min Act: -0.1700
Data Index: 6935839 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.1415. Min Act: -0.1700
Data Index: 3053395 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.1103. Min Act: -0.1700
Data Index: 5316743 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.1103. Min Act: -0.1700
Data Index: 3873872 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.1415. Min Act: -0.1700
Data Index: 5001735 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0790. Min Act: -0.1700
Data Index: 7041067 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0165. Min Act: -0.1700
Data Index: 410882 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0478. Min Act: -0.1700
Data Index: 1442843 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0478. Min Act: -0.1700
Data Index: 8550071 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0165. Min Act: -0.1700
Data Index: 3969331 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0478. Min Act: -0.1700
Data Index: 8801095 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0478. Min Act: -0.1700
Data Index: 8550068 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0478. Min Act: -0.1700
Data Index: 4740712 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0165. Min Act: -0.1700
Data Index: 5746200 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0165. Min Act: -0.1700
Data Index: 2207097 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0165. Min Act: -0.1700
Data Index: 6773070 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1728. Min Range: -5.1728
Max Act: 5.0165. Min Act: -0.1700
Data Index: 8801097 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1728. Min Range: -5.1728
Max Act: 4.9853. Min Act: -0.1700
Data Index: 4632568 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19