Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4786. Min Range: -6.4786
Max Act: 6.4786. Min Act: -0.1700
Data Index: 3624416 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4786. Min Range: -6.4786
Max Act: 6.3223. Min Act: -0.1700
Data Index: 6393606 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4786. Min Range: -6.4786
Max Act: 6.2598. Min Act: -0.1700
Data Index: 682501 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4786. Min Range: -6.4786
Max Act: 6.0411. Min Act: -0.1700
Data Index: 6375886 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4786. Min Range: -6.4786
Max Act: 6.0411. Min Act: -0.1700
Data Index: 3399991 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4786. Min Range: -6.4786
Max Act: 6.0411. Min Act: -0.1700
Data Index: 4102913 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.9786. Min Act: -0.1700
Data Index: 2588865 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.9161. Min Act: -0.1700
Data Index: 1228712 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.9161. Min Act: -0.1700
Data Index: 8226596 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.8848. Min Act: -0.1700
Data Index: 4131903 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.8848. Min Act: -0.1700
Data Index: 8101094 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.8223. Min Act: -0.1700
Data Index: 1139466 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.8536. Min Act: -0.1700
Data Index: 7123100 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.8223. Min Act: -0.1700
Data Index: 6630541 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.7911. Min Act: -0.1700
Data Index: 4571749 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.7911. Min Act: -0.1700
Data Index: 538387 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.7286. Min Act: -0.1700
Data Index: 2224535 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.6973. Min Act: -0.1700
Data Index: 1053830 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.6973. Min Act: -0.1700
Data Index: 364880 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4786. Min Range: -6.4786
Max Act: 5.6973. Min Act: -0.1700
Data Index: 4131902 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19