Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2418 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5690. Min Act: -0.1700
Data Index: 8267680 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5419. Min Act: -0.1700
Data Index: 838611 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5362. Min Act: -0.1700
Data Index: 7005054 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5419. Min Act: -0.1700
Data Index: 2105869 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5267. Min Act: -0.1700
Data Index: 1563259 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5058. Min Act: -0.1700
Data Index: 6278182 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.4824. Min Act: -0.1700
Data Index: 1615855 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5162. Min Act: -0.1700
Data Index: 1155638 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5134. Min Act: -0.1700
Data Index: 3965568 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5077. Min Act: -0.1700
Data Index: 6068504 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5030. Min Act: -0.1700
Data Index: 4560963 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5068. Min Act: -0.1700
Data Index: 1733887 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5030. Min Act: -0.1700
Data Index: 2493076 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.4918. Min Act: -0.1700
Data Index: 3439730 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5068. Min Act: -0.1700
Data Index: 1845661 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5124. Min Act: -0.1700
Data Index: 8027385 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.4927. Min Act: -0.1700
Data Index: 6896989 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.4992. Min Act: -0.1700
Data Index: 7169902 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.4983. Min Act: -0.1700
Data Index: 7279754 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5690. Min Range: -0.5690
Max Act: 0.5002. Min Act: -0.1700
Data Index: 2804290 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19