Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5076 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.8144. Min Act: -0.1700
Data Index: 5063370 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.7519. Min Act: -0.1700
Data Index: 5769291 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.7207. Min Act: -0.1700
Data Index: 4067638 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.7207. Min Act: -0.1700
Data Index: 6414141 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.7207. Min Act: -0.1700
Data Index: 5128462 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.7207. Min Act: -0.1700
Data Index: 6488552 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.7207. Min Act: -0.1700
Data Index: 2234009 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6894. Min Act: -0.1700
Data Index: 8737482 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6894. Min Act: -0.1700
Data Index: 4923843 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6582. Min Act: -0.1700
Data Index: 5918211 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6582. Min Act: -0.1700
Data Index: 7461647 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6582. Min Act: -0.1700
Data Index: 6335012 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6582. Min Act: -0.1700
Data Index: 8684174 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6269. Min Act: -0.1700
Data Index: 1467839 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6269. Min Act: -0.1700
Data Index: 4725320 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6269. Min Act: -0.1700
Data Index: 6236136 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6269. Min Act: -0.1700
Data Index: 7894670 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.6269. Min Act: -0.1700
Data Index: 6477323 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.5957. Min Act: -0.1700
Data Index: 3950542 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8144. Min Range: -5.8144
Max Act: 5.5957. Min Act: -0.1700
Data Index: 8702965 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19