Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1716 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.5237. Min Act: -0.1578
Data Index: 3621951 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4798. Min Act: -0.1700
Data Index: 2118799 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4535. Min Act: -0.1698
Data Index: 6409874 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4535. Min Act: -0.1700
Data Index: 5834581 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4359. Min Act: -0.1687
Data Index: 288399 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4447. Min Act: -0.1700
Data Index: 5460161 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4271. Min Act: -0.1699
Data Index: 3426751 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4183. Min Act: -0.1700
Data Index: 3063245 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4095. Min Act: -0.1700
Data Index: 2562531 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4095. Min Act: -0.1700
Data Index: 2574732 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4095. Min Act: -0.1700
Data Index: 588190 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4095. Min Act: -0.1698
Data Index: 3738153 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4006. Min Act: -0.1699
Data Index: 1949331 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.4006. Min Act: -0.1700
Data Index: 2569668 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.3918. Min Act: -0.1700
Data Index: 5344759 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.3918. Min Act: -0.1700
Data Index: 3705074 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.3830. Min Act: -0.1700
Data Index: 255100 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.3918. Min Act: -0.1700
Data Index: 4824884 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.3830. Min Act: -0.1698
Data Index: 5044331 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5237. Min Range: -1.5237
Max Act: 1.3830. Min Act: -0.1700
Data Index: 5284465 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19