Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1861 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.2144. Min Act: -0.1700
Data Index: 5650394 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1206. Min Act: -0.1700
Data Index: 2537032 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 1088020 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9331. Min Act: -0.1700
Data Index: 4661175 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 7833686 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9331. Min Act: -0.1700
Data Index: 2939369 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 154044 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8706. Min Act: -0.1700
Data Index: 7136425 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 3735861 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 6979838 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8706. Min Act: -0.1700
Data Index: 7225648 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 8138196 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 7265410 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 3633495 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 3937268 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 6455051 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 7500677 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7456. Min Act: -0.1700
Data Index: 3585806 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7456. Min Act: -0.1700
Data Index: 3136851 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 4402861 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19