Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1912. Min Range: -5.1912
Max Act: 5.1912. Min Act: -0.1700
Data Index: 1012907 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1912. Min Range: -5.1912
Max Act: 5.0662. Min Act: -0.1700
Data Index: 390012 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1912. Min Range: -5.1912
Max Act: 5.0349. Min Act: -0.1700
Data Index: 7640923 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.9412. Min Act: -0.1700
Data Index: 7057615 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.9412. Min Act: -0.1700
Data Index: 1287130 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.9099. Min Act: -0.1700
Data Index: 7842074 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.9099. Min Act: -0.1700
Data Index: 2935173 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8787. Min Act: -0.1700
Data Index: 5549864 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8787. Min Act: -0.1700
Data Index: 5549866 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8474. Min Act: -0.1700
Data Index: 7842072 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8474. Min Act: -0.1700
Data Index: 5549869 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8474. Min Act: -0.1700
Data Index: 3305203 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8474. Min Act: -0.1700
Data Index: 5549873 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8162. Min Act: -0.1700
Data Index: 6330907 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8162. Min Act: -0.1700
Data Index: 5549863 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8162. Min Act: -0.1700
Data Index: 1048934 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.8474. Min Act: -0.1700
Data Index: 5549858 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.7849. Min Act: -0.1700
Data Index: 7634821 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.7849. Min Act: -0.1700
Data Index: 5549855 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1912. Min Range: -5.1912
Max Act: 4.7224. Min Act: -0.1700
Data Index: 5549852 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19