Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.2040. Min Act: -0.1693
Data Index: 234889 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.2040. Min Act: -0.1699
Data Index: 520600 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.1103. Min Act: -0.1700
Data Index: 631127 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.1103. Min Act: -0.1700
Data Index: 5894835 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.1103. Min Act: -0.1700
Data Index: 3550803 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0790. Min Act: -0.1700
Data Index: 1732994 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0478. Min Act: -0.1700
Data Index: 1323143 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0790. Min Act: -0.1688
Data Index: 2149664 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0790. Min Act: -0.1700
Data Index: 284280 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0478. Min Act: -0.1681
Data Index: 7045340 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0478. Min Act: -0.1700
Data Index: 906686 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0478. Min Act: -0.1700
Data Index: 7677041 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2040. Min Range: -5.2040
Max Act: 4.9853. Min Act: -0.1698
Data Index: 8818723 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0165. Min Act: -0.1700
Data Index: 1529264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0165. Min Act: -0.1700
Data Index: 3844150 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0165. Min Act: -0.1700
Data Index: 6511976 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0165. Min Act: -0.1699
Data Index: 5701805 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0165. Min Act: -0.1696
Data Index: 1798326 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2040. Min Range: -5.2040
Max Act: 5.0165. Min Act: -0.1700
Data Index: 1829984 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2040. Min Range: -5.2040
Max Act: 4.9540. Min Act: -0.1700
Data Index: 2783631 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19