Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3905 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0081. Min Range: -1.0081
Max Act: 1.0081. Min Act: -0.1695
Data Index: 312608 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9561. Min Act: -0.1688
Data Index: 7485826 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9734. Min Act: -0.1700
Data Index: 4602440 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9561. Min Act: -0.1693
Data Index: 6823284 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9561. Min Act: -0.1700
Data Index: 7663899 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9389. Min Act: -0.1698
Data Index: 8549448 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9303. Min Act: -0.1700
Data Index: 7591152 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9303. Min Act: -0.1700
Data Index: 126258 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9303. Min Act: -0.1700
Data Index: 5111182 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9217. Min Act: -0.1700
Data Index: 3252732 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9131. Min Act: -0.1679
Data Index: 5969984 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9131. Min Act: -0.1697
Data Index: 17082 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9046. Min Act: -0.1700
Data Index: 2824220 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9131. Min Act: -0.1696
Data Index: 6440379 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9046. Min Act: -0.1698
Data Index: 34106 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9046. Min Act: -0.1698
Data Index: 498408 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.8960. Min Act: -0.1700
Data Index: 2128488 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9131. Min Act: -0.1700
Data Index: 2244007 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.9131. Min Act: -0.1700
Data Index: 2616859 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0081. Min Range: -1.0081
Max Act: 0.8960. Min Act: -0.1698
Data Index: 4412053 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19