Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.8726. Min Act: -0.1700
Data Index: 394540 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.8101. Min Act: -0.1700
Data Index: 1945810 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.8101. Min Act: -0.1700
Data Index: 5520857 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.7789. Min Act: -0.1700
Data Index: 7784228 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.7164. Min Act: -0.1700
Data Index: 3930899 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.6539. Min Act: -0.1700
Data Index: 4508360 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.6226. Min Act: -0.1700
Data Index: 2692189 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.6226. Min Act: -0.1700
Data Index: 2602104 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5914. Min Act: -0.1700
Data Index: 7381344 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5601. Min Act: -0.1700
Data Index: 1292902 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5601. Min Act: -0.1700
Data Index: 1579913 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5601. Min Act: -0.1700
Data Index: 366330 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5601. Min Act: -0.1700
Data Index: 5961826 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5601. Min Act: -0.1700
Data Index: 690581 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5914. Min Act: -0.1700
Data Index: 6984757 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.4976. Min Act: -0.1700
Data Index: 2084577 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5289. Min Act: -0.1700
Data Index: 5201140 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5289. Min Act: -0.1700
Data Index: 4878735 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5289. Min Act: -0.1700
Data Index: 4352898 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8726. Min Range: -5.8726
Max Act: 5.5289. Min Act: -0.1700
Data Index: 3538241 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19