Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1455 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.4876. Min Act: -0.1700
Data Index: 6204315 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.4093. Min Act: -0.1700
Data Index: 1768527 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.3936. Min Act: -0.1700
Data Index: 1233633 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2837. Min Act: -0.1700
Data Index: 3398753 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2680. Min Act: -0.1700
Data Index: 2866395 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2523. Min Act: -0.1700
Data Index: 1001255 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2680. Min Act: -0.1700
Data Index: 5144891 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2680. Min Act: -0.1700
Data Index: 7770450 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2209. Min Act: -0.1700
Data Index: 4905112 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2052. Min Act: -0.1700
Data Index: 843663 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2052. Min Act: -0.1700
Data Index: 6676283 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.2052. Min Act: -0.1700
Data Index: 3454009 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.1737. Min Act: -0.1700
Data Index: 6667889 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.1580. Min Act: -0.1700
Data Index: 7298535 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.1580. Min Act: -0.1700
Data Index: 784840 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.1580. Min Act: -0.1700
Data Index: 227860 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.1737. Min Act: -0.1700
Data Index: 5286311 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.1580. Min Act: -0.1700
Data Index: 1288015 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.1580. Min Act: -0.1700
Data Index: 2309176 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4876. Min Range: -3.4876
Max Act: 3.1265. Min Act: -0.1700
Data Index: 2863500 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19