Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.7830. Min Act: -0.1700
Data Index: 160616 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.7205. Min Act: -0.1700
Data Index: 2259897 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6892. Min Act: -0.1700
Data Index: 4931054 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6267. Min Act: -0.1700
Data Index: 4325614 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6267. Min Act: -0.1700
Data Index: 5103436 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5955. Min Act: -0.1700
Data Index: 2259896 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5955. Min Act: -0.1700
Data Index: 5152232 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5955. Min Act: -0.1700
Data Index: 3924873 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5642. Min Act: -0.1700
Data Index: 4680768 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5329. Min Act: -0.1700
Data Index: 2259894 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5329. Min Act: -0.1700
Data Index: 8662303 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5017. Min Act: -0.1700
Data Index: 2708613 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5017. Min Act: -0.1700
Data Index: 396472 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5017. Min Act: -0.1700
Data Index: 7425956 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5329. Min Act: -0.1700
Data Index: 3838191 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5017. Min Act: -0.1700
Data Index: 8813946 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.4704. Min Act: -0.1700
Data Index: 298989 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.4704. Min Act: -0.1700
Data Index: 3190608 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.4704. Min Act: -0.1700
Data Index: 2259893 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5017. Min Act: -0.1700
Data Index: 3190616 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19