Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.3265. Min Act: -0.1700
Data Index: 2139735 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.1702. Min Act: -0.1700
Data Index: 5263308 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.1390. Min Act: -0.1700
Data Index: 6341503 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.1077. Min Act: -0.1700
Data Index: 6180689 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.0765. Min Act: -0.1700
Data Index: 2636357 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.0765. Min Act: -0.1700
Data Index: 98456 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.0452. Min Act: -0.1700
Data Index: 8722309 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.0765. Min Act: -0.1700
Data Index: 4924844 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3265. Min Range: -4.3265
Max Act: 4.0140. Min Act: -0.1700
Data Index: 7827340 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.9202. Min Act: -0.1700
Data Index: 8740532 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8889. Min Act: -0.1700
Data Index: 725827 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8889. Min Act: -0.1700
Data Index: 548716 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8889. Min Act: -0.1700
Data Index: 3746893 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8576. Min Act: -0.1700
Data Index: 1044466 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8889. Min Act: -0.1700
Data Index: 7710767 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8576. Min Act: -0.1700
Data Index: 6038734 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8576. Min Act: -0.1700
Data Index: 1697318 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8264. Min Act: -0.1700
Data Index: 847916 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8264. Min Act: -0.1700
Data Index: 2534713 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3265. Min Range: -4.3265
Max Act: 3.8264. Min Act: -0.1700
Data Index: 5209956 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19