Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2291 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.8440. Min Act: -0.1700
Data Index: 5171690 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.6252. Min Act: -0.1700
Data Index: 2332816 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.5002. Min Act: -0.1700
Data Index: 2144441 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.4690. Min Act: -0.1700
Data Index: 5329055 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.4690. Min Act: -0.1700
Data Index: 245886 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.4690. Min Act: -0.1700
Data Index: 1006131 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.4690. Min Act: -0.1700
Data Index: 8328355 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.4690. Min Act: -0.1700
Data Index: 8397235 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3440. Min Act: -0.1700
Data Index: 648104 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3440. Min Act: -0.1700
Data Index: 5335233 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3440. Min Act: -0.1700
Data Index: 2991805 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3127. Min Act: -0.1700
Data Index: 4025894 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3440. Min Act: -0.1700
Data Index: 5541342 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3127. Min Act: -0.1700
Data Index: 7717574 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3127. Min Act: -0.1700
Data Index: 229960 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.2815. Min Act: -0.1700
Data Index: 2997166 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3127. Min Act: -0.1700
Data Index: 5198756 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.3127. Min Act: -0.1700
Data Index: 6802233 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.2815. Min Act: -0.1700
Data Index: 3632818 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8440. Min Range: -6.8440
Max Act: 6.2815. Min Act: -0.1700
Data Index: 798141 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19