Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0186. Min Range: -2.0186
Max Act: 2.0017. Min Act: -0.1700
Data Index: 6142795 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0186. Min Range: -2.0186
Max Act: 2.0017. Min Act: -0.1700
Data Index: 6630576 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0186. Min Range: -2.0186
Max Act: 2.0186. Min Act: -0.1700
Data Index: 7570904 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0186. Min Range: -2.0186
Max Act: 2.0017. Min Act: -0.1700
Data Index: 8026895 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0186. Min Range: -2.0186
Max Act: 2.0017. Min Act: -0.1700
Data Index: 4271741 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9848. Min Act: -0.1700
Data Index: 2376167 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9679. Min Act: -0.1700
Data Index: 7191758 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9848. Min Act: -0.1700
Data Index: 1960930 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0186. Min Range: -2.0186
Max Act: 2.0017. Min Act: -0.1700
Data Index: 4410891 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9848. Min Act: -0.1700
Data Index: 2355466 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9848. Min Act: -0.1700
Data Index: 2396545 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9848. Min Act: -0.1700
Data Index: 8528165 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9679. Min Act: -0.1700
Data Index: 419722 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9509. Min Act: -0.1700
Data Index: 3978492 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9679. Min Act: -0.1700
Data Index: 5935809 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9848. Min Act: -0.1700
Data Index: 6602518 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9679. Min Act: -0.1700
Data Index: 5849368 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9679. Min Act: -0.1700
Data Index: 4638590 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9509. Min Act: -0.1700
Data Index: 6630575 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0186. Min Range: -2.0186
Max Act: 1.9509. Min Act: -0.1700
Data Index: 6717039 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19