Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.3328. Min Act: -0.1700
Data Index: 4413461 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.2391. Min Act: -0.1700
Data Index: 8266104 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.1453. Min Act: -0.1700
Data Index: 8750231 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.1766. Min Act: -0.1700
Data Index: 269714 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.1141. Min Act: -0.1700
Data Index: 5281766 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.1141. Min Act: -0.1700
Data Index: 7023936 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.1141. Min Act: -0.1700
Data Index: 1304546 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.0828. Min Act: -0.1700
Data Index: 5760277 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3328. Min Range: -5.3328
Max Act: 5.0516. Min Act: -0.1700
Data Index: 3321150 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8953. Min Act: -0.1700
Data Index: 4087296 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8953. Min Act: -0.1700
Data Index: 1763536 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7107999 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8953. Min Act: -0.1700
Data Index: 3242604 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8641. Min Act: -0.1700
Data Index: 866714 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8641. Min Act: -0.1700
Data Index: 8129652 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8328. Min Act: -0.1700
Data Index: 7332894 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8328. Min Act: -0.1700
Data Index: 3925616 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8016. Min Act: -0.1700
Data Index: 6261928 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8016. Min Act: -0.1700
Data Index: 7859153 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3328. Min Range: -5.3328
Max Act: 4.8016. Min Act: -0.1700
Data Index: 7863426 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19