Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3982 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4298. Min Range: -7.4298
Max Act: 7.4298. Min Act: -0.1700
Data Index: 7257242 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.9923. Min Act: -0.1700
Data Index: 5101925 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.8985. Min Act: -0.1700
Data Index: 4278676 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.9610. Min Act: -0.1700
Data Index: 1429616 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.8360. Min Act: -0.1700
Data Index: 294149 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.8360. Min Act: -0.1700
Data Index: 2583346 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.7735. Min Act: -0.1700
Data Index: 8074578 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.7110. Min Act: -0.1700
Data Index: 5837208 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.7110. Min Act: -0.1700
Data Index: 50773 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.7110. Min Act: -0.1700
Data Index: 6770155 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.6798. Min Act: -0.1700
Data Index: 3922298 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.7110. Min Act: -0.1700
Data Index: 5964605 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.6173. Min Act: -0.1700
Data Index: 2883408 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.6173. Min Act: -0.1700
Data Index: 1142393 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.5860. Min Act: -0.1700
Data Index: 3306897 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.5548. Min Act: -0.1700
Data Index: 4173827 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.5548. Min Act: -0.1700
Data Index: 5361308 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.5548. Min Act: -0.1700
Data Index: 7670549 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.5548. Min Act: -0.1700
Data Index: 2281552 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4298. Min Range: -7.4298
Max Act: 6.5548. Min Act: -0.1700
Data Index: 7046321 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19