Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4865 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0729. Min Range: -10.0729
Max Act: 10.0729. Min Act: -0.1700
Data Index: 6603245 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0729. Min Range: -10.0729
Max Act: 10.0104. Min Act: -0.1700
Data Index: 959842 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.9479. Min Act: -0.1700
Data Index: 6736742 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.9479. Min Act: -0.1700
Data Index: 7195322 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.7604. Min Act: -0.1700
Data Index: 4201531 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.7604. Min Act: -0.1700
Data Index: 6651250 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6354. Min Act: -0.1700
Data Index: 2368818 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6979. Min Act: -0.1700
Data Index: 4286234 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6979. Min Act: -0.1700
Data Index: 5739774 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6979. Min Act: -0.1700
Data Index: 8210316 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6354. Min Act: -0.1700
Data Index: 3504631 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6354. Min Act: -0.1700
Data Index: 128508 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6354. Min Act: -0.1700
Data Index: 875222 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.5729. Min Act: -0.1700
Data Index: 4847133 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6354. Min Act: -0.1700
Data Index: 8053407 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.6354. Min Act: -0.1700
Data Index: 1500772 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.5729. Min Act: -0.1700
Data Index: 8251941 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.5729. Min Act: -0.1700
Data Index: 7292395 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.5729. Min Act: -0.1700
Data Index: 473920 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0729. Min Range: -10.0729
Max Act: 9.5729. Min Act: -0.1700
Data Index: 2635779 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19