Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5720 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5180. Min Range: -7.5180
Max Act: 7.5180. Min Act: -0.1700
Data Index: 7865441 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.9555. Min Act: -0.1700
Data Index: 1228965 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.5805. Min Act: -0.1700
Data Index: 7220500 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.6117. Min Act: -0.1700
Data Index: 8425987 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.5805. Min Act: -0.1700
Data Index: 3619549 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.5492. Min Act: -0.1700
Data Index: 2044831 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.5180. Min Act: -0.1700
Data Index: 1283626 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.4555. Min Act: -0.1700
Data Index: 1364446 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.4555. Min Act: -0.1700
Data Index: 7173850 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.4242. Min Act: -0.1700
Data Index: 5777721 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.3930. Min Act: -0.1700
Data Index: 8754647 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.4242. Min Act: -0.1700
Data Index: 8508882 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.3617. Min Act: -0.1700
Data Index: 865155 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.3930. Min Act: -0.1700
Data Index: 3998747 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.3617. Min Act: -0.1700
Data Index: 806814 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.3930. Min Act: -0.1700
Data Index: 2750699 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.3617. Min Act: -0.1700
Data Index: 1422065 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.2992. Min Act: -0.1700
Data Index: 7180462 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.3305. Min Act: -0.1700
Data Index: 4528783 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5180. Min Range: -7.5180
Max Act: 6.3305. Min Act: -0.1700
Data Index: 5435308 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19