Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.9369. Min Act: -0.1700
Data Index: 7869187 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.9369. Min Act: -0.1700
Data Index: 1162962 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.9369. Min Act: -0.1700
Data Index: 8350375 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.8744. Min Act: -0.1700
Data Index: 2392971 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.7494. Min Act: -0.1700
Data Index: 1184351 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.6869. Min Act: -0.1700
Data Index: 8607770 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.5619. Min Act: -0.1700
Data Index: 6999242 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.4994. Min Act: -0.1700
Data Index: 5486022 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.4369. Min Act: -0.1700
Data Index: 2527743 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.4369. Min Act: -0.1700
Data Index: 639166 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.3744. Min Act: -0.1700
Data Index: 5672392 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.3119. Min Act: -0.1700
Data Index: 4178958 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.1869. Min Act: -0.1700
Data Index: 2058041 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.2494. Min Act: -0.1700
Data Index: 8092223 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.2494. Min Act: -0.1700
Data Index: 7578225 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.1244. Min Act: -0.1700
Data Index: 3121569 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.1244. Min Act: -0.1700
Data Index: 6905044 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9369. Min Range: -10.9369
Max Act: 10.0619. Min Act: -0.1700
Data Index: 6656131 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9369. Min Range: -10.9369
Max Act: 9.9994. Min Act: -0.1700
Data Index: 8654862 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9369. Min Range: -10.9369
Max Act: 9.8744. Min Act: -0.1700
Data Index: 1849032 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19