Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4124 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2353. Min Range: -6.2353
Max Act: 6.2353. Min Act: -0.1700
Data Index: 2152313 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2353. Min Range: -6.2353
Max Act: 6.2353. Min Act: -0.1700
Data Index: 5511170 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2353. Min Range: -6.2353
Max Act: 6.1728. Min Act: -0.1700
Data Index: 6724354 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2353. Min Range: -6.2353
Max Act: 6.1415. Min Act: -0.1700
Data Index: 4987564 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2353. Min Range: -6.2353
Max Act: 6.1103. Min Act: -0.1700
Data Index: 820980 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2353. Min Range: -6.2353
Max Act: 6.0790. Min Act: -0.1700
Data Index: 4896126 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2353. Min Range: -6.2353
Max Act: 6.0478. Min Act: -0.1700
Data Index: 934497 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2353. Min Range: -6.2353
Max Act: 6.0165. Min Act: -0.1700
Data Index: 6659438 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.9853. Min Act: -0.1700
Data Index: 6272665 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.9540. Min Act: -0.1700
Data Index: 996468 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.9540. Min Act: -0.1700
Data Index: 7385580 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.9540. Min Act: -0.1700
Data Index: 8261811 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.8915. Min Act: -0.1700
Data Index: 2435560 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.9228. Min Act: -0.1700
Data Index: 1841663 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.8915. Min Act: -0.1700
Data Index: 220275 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.9228. Min Act: -0.1700
Data Index: 490664 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.8915. Min Act: -0.1700
Data Index: 4870816 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.8603. Min Act: -0.1700
Data Index: 658077 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.8915. Min Act: -0.1700
Data Index: 1591594 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2353. Min Range: -6.2353
Max Act: 5.8915. Min Act: -0.1700
Data Index: 2271015 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19