Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.8687. Min Act: -0.1700
Data Index: 4300302 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.8062. Min Act: -0.1700
Data Index: 5802646 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.7437. Min Act: -0.1700
Data Index: 650615 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.7437. Min Act: -0.1700
Data Index: 5511384 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.6812. Min Act: -0.1700
Data Index: 4040145 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.6187. Min Act: -0.1700
Data Index: 4010334 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.5875. Min Act: -0.1700
Data Index: 3441553 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.5562. Min Act: -0.1700
Data Index: 7725684 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.4937. Min Act: -0.1700
Data Index: 1967330 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.4937. Min Act: -0.1700
Data Index: 5541217 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.4937. Min Act: -0.1700
Data Index: 1586913 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.4625. Min Act: -0.1700
Data Index: 4036799 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.4625. Min Act: -0.1700
Data Index: 2878187 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.3687. Min Act: -0.1700
Data Index: 6574337 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.3375. Min Act: -0.1700
Data Index: 2761859 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.3062. Min Act: -0.1700
Data Index: 2053647 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.3375. Min Act: -0.1700
Data Index: 2425047 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.3375. Min Act: -0.1700
Data Index: 4537478 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.3687. Min Act: -0.1700
Data Index: 5567852 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8687. Min Range: -7.8687
Max Act: 7.3062. Min Act: -0.1700
Data Index: 6170431 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19