Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.7629. Min Act: -0.1700
Data Index: 3698853 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.7629. Min Act: -0.1700
Data Index: 6771729 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.6379. Min Act: -0.1700
Data Index: 6483503 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.4817. Min Act: -0.1700
Data Index: 7453300 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.4192. Min Act: -0.1700
Data Index: 4442571 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.2317. Min Act: -0.1700
Data Index: 7556078 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.2317. Min Act: -0.1700
Data Index: 2193643 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.2004. Min Act: -0.1700
Data Index: 466994 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.2004. Min Act: -0.1700
Data Index: 7880074 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1692. Min Act: -0.1700
Data Index: 6476844 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1692. Min Act: -0.1700
Data Index: 4370495 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1692. Min Act: -0.1700
Data Index: 3407717 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1692. Min Act: -0.1700
Data Index: 883160 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1692. Min Act: -0.1700
Data Index: 1103011 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1379. Min Act: -0.1700
Data Index: 881011 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1379. Min Act: -0.1700
Data Index: 5793903 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1379. Min Act: -0.1700
Data Index: 7637239 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1379. Min Act: -0.1700
Data Index: 6597129 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1692. Min Act: -0.1700
Data Index: 2863552 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7629. Min Range: -5.7629
Max Act: 5.1379. Min Act: -0.1700
Data Index: 5999608 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19