Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.4372. Min Range: -13.4372
Max Act: 13.4372. Min Act: -0.1700
Data Index: 6954608 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.4372. Min Range: -13.4372
Max Act: 13.2497. Min Act: -0.1700
Data Index: 6954599 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.4372. Min Range: -13.4372
Max Act: 13.1872. Min Act: -0.1700
Data Index: 3831665 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.4372. Min Range: -13.4372
Max Act: 13.1247. Min Act: -0.1700
Data Index: 4948034 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.4372. Min Range: -13.4372
Max Act: 13.0622. Min Act: -0.1700
Data Index: 6954594 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.7497. Min Act: -0.1700
Data Index: 708281 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.7497. Min Act: -0.1700
Data Index: 3240000 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.6247. Min Act: -0.1700
Data Index: 6954601 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.3122. Min Act: -0.1700
Data Index: 7067865 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.3122. Min Act: -0.1700
Data Index: 7067860 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.1872. Min Act: -0.1700
Data Index: 7067862 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.1872. Min Act: -0.1700
Data Index: 2166104 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.1247. Min Act: -0.1700
Data Index: 7067861 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.1872. Min Act: -0.1700
Data Index: 7470403 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.1247. Min Act: -0.1700
Data Index: 6194119 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.1872. Min Act: -0.1700
Data Index: 2293895 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.1872. Min Act: -0.1700
Data Index: 6954596 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.0622. Min Act: -0.1700
Data Index: 2213839 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.4372. Min Range: -13.4372
Max Act: 12.0622. Min Act: -0.1700
Data Index: 8309119 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.4372. Min Range: -13.4372
Max Act: 11.9997. Min Act: -0.1700
Data Index: 6106527 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19