Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1630. Min Range: -6.1630
Max Act: 6.1630. Min Act: -0.1700
Data Index: 4925471 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1630. Min Range: -6.1630
Max Act: 6.1630. Min Act: -0.1700
Data Index: 1432780 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1630. Min Range: -6.1630
Max Act: 6.1630. Min Act: -0.1700
Data Index: 3245323 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1630. Min Range: -6.1630
Max Act: 6.0380. Min Act: -0.1700
Data Index: 1829544 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1630. Min Range: -6.1630
Max Act: 6.1005. Min Act: -0.1700
Data Index: 725000 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1630. Min Range: -6.1630
Max Act: 6.0380. Min Act: -0.1700
Data Index: 8736558 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1630. Min Range: -6.1630
Max Act: 6.0380. Min Act: -0.1700
Data Index: 1608673 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.9442. Min Act: -0.1700
Data Index: 3753798 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.9442. Min Act: -0.1700
Data Index: 5671778 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.9130. Min Act: -0.1700
Data Index: 1170723 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8817. Min Act: -0.1700
Data Index: 5451374 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8817. Min Act: -0.1700
Data Index: 4296453 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8817. Min Act: -0.1700
Data Index: 4266722 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8817. Min Act: -0.1700
Data Index: 5224189 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.9130. Min Act: -0.1700
Data Index: 253695 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8817. Min Act: -0.1700
Data Index: 7897535 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8505. Min Act: -0.1700
Data Index: 7007345 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8505. Min Act: -0.1700
Data Index: 1025177 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8505. Min Act: -0.1700
Data Index: 7325172 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1630. Min Range: -6.1630
Max Act: 5.8192. Min Act: -0.1700
Data Index: 587301 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19