Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.2309. Min Act: -0.1700
Data Index: 6930817 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.1684. Min Act: -0.1700
Data Index: 8209892 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.1997. Min Act: -0.1700
Data Index: 4553493 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.1372. Min Act: -0.1700
Data Index: 1859710 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.1372. Min Act: -0.1700
Data Index: 8594799 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.1059. Min Act: -0.1700
Data Index: 4076102 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.1059. Min Act: -0.1700
Data Index: 1994054 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0747. Min Act: -0.1700
Data Index: 1038978 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0747. Min Act: -0.1700
Data Index: 6034487 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0747. Min Act: -0.1700
Data Index: 5919742 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0747. Min Act: -0.1700
Data Index: 7736594 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.1059. Min Act: -0.1700
Data Index: 7562875 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 1318020 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 4090547 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 457050 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 821648 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0434. Min Act: -0.1700
Data Index: 5919740 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0122. Min Act: -0.1700
Data Index: 7242122 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0122. Min Act: -0.1700
Data Index: 5560713 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2309. Min Range: -5.2309
Max Act: 5.0122. Min Act: -0.1700
Data Index: 2417504 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19