Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 380 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.2317. Min Act: -0.1700
Data Index: 2007989 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.2004. Min Act: -0.1700
Data Index: 3226995 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.1692. Min Act: -0.1700
Data Index: 3966513 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.1379. Min Act: -0.1700
Data Index: 7982682 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.1379. Min Act: -0.1700
Data Index: 7653038 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.0754. Min Act: -0.1700
Data Index: 2154543 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.0754. Min Act: -0.1700
Data Index: 1178801 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.0754. Min Act: -0.1700
Data Index: 3397761 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.0754. Min Act: -0.1700
Data Index: 5547434 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.0442. Min Act: -0.1700
Data Index: 2640955 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.0129. Min Act: -0.1700
Data Index: 5500671 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.0129. Min Act: -0.1700
Data Index: 5377480 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2317. Min Range: -5.2317
Max Act: 5.0129. Min Act: -0.1700
Data Index: 888030 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2317. Min Range: -5.2317
Max Act: 4.9504. Min Act: -0.1700
Data Index: 2835605 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2317. Min Range: -5.2317
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4052522 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2317. Min Range: -5.2317
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4642809 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2317. Min Range: -5.2317
Max Act: 4.8879. Min Act: -0.1700
Data Index: 9845 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2317. Min Range: -5.2317
Max Act: 4.8879. Min Act: -0.1700
Data Index: 5377124 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2317. Min Range: -5.2317
Max Act: 4.9192. Min Act: -0.1700
Data Index: 2692609 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2317. Min Range: -5.2317
Max Act: 4.8567. Min Act: -0.1700
Data Index: 3646418 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19