Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.7140. Min Act: -0.1700
Data Index: 1259318 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.6828. Min Act: -0.1700
Data Index: 8256102 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.6828. Min Act: -0.1700
Data Index: 4766446 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.6515. Min Act: -0.1700
Data Index: 8051684 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.6515. Min Act: -0.1700
Data Index: 5935099 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.4953. Min Act: -0.1700
Data Index: 768727 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.5265. Min Act: -0.1700
Data Index: 3873200 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.4953. Min Act: -0.1700
Data Index: 5659408 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.4953. Min Act: -0.1700
Data Index: 7048028 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.4640. Min Act: -0.1700
Data Index: 6170779 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.4640. Min Act: -0.1700
Data Index: 1937513 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.4640. Min Act: -0.1700
Data Index: 5266013 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.4015. Min Act: -0.1700
Data Index: 1706799 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.3703. Min Act: -0.1700
Data Index: 577121 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.3703. Min Act: -0.1700
Data Index: 1112320 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.3390. Min Act: -0.1700
Data Index: 5919185 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.3078. Min Act: -0.1700
Data Index: 1650149 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.3078. Min Act: -0.1700
Data Index: 6328050 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.3078. Min Act: -0.1700
Data Index: 1466934 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7140. Min Range: -6.7140
Max Act: 6.3078. Min Act: -0.1700
Data Index: 5375358 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19