Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2406 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.5602. Min Act: -0.1700
Data Index: 2051470 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.5914. Min Act: -0.1700
Data Index: 551889 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.5289. Min Act: -0.1700
Data Index: 6763494 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.5602. Min Act: -0.1700
Data Index: 5796741 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4977. Min Act: -0.1700
Data Index: 5204726 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4352. Min Act: -0.1700
Data Index: 8699605 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4352. Min Act: -0.1700
Data Index: 2268863 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3727. Min Act: -0.1700
Data Index: 866929 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3414. Min Act: -0.1700
Data Index: 2318569 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3414. Min Act: -0.1700
Data Index: 8572512 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3414. Min Act: -0.1700
Data Index: 7057562 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3727. Min Act: -0.1700
Data Index: 1129844 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3102. Min Act: -0.1700
Data Index: 6356150 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3102. Min Act: -0.1700
Data Index: 6821896 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.2789. Min Act: -0.1700
Data Index: 3678605 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3414. Min Act: -0.1700
Data Index: 4413841 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3102. Min Act: -0.1700
Data Index: 4396945 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3414. Min Act: -0.1700
Data Index: 6420445 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.2789. Min Act: -0.1700
Data Index: 77314 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.2789. Min Act: -0.1700
Data Index: 218129 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19