Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5300 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2777. Min Range: -5.2777
Max Act: 5.2777. Min Act: -0.1700
Data Index: 2332450 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2777. Min Range: -5.2777
Max Act: 5.2465. Min Act: -0.1700
Data Index: 6185525 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2777. Min Range: -5.2777
Max Act: 5.1527. Min Act: -0.1700
Data Index: 5473649 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2777. Min Range: -5.2777
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3255253 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2777. Min Range: -5.2777
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3088356 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2777. Min Range: -5.2777
Max Act: 5.0277. Min Act: -0.1700
Data Index: 808983 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2777. Min Range: -5.2777
Max Act: 5.0277. Min Act: -0.1700
Data Index: 2928179 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9965. Min Act: -0.1700
Data Index: 1432152 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9965. Min Act: -0.1700
Data Index: 8744458 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9652. Min Act: -0.1700
Data Index: 4187577 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9652. Min Act: -0.1700
Data Index: 7293760 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9652. Min Act: -0.1700
Data Index: 3474880 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9652. Min Act: -0.1700
Data Index: 5370072 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9340. Min Act: -0.1700
Data Index: 1725624 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9340. Min Act: -0.1700
Data Index: 4878888 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.9340. Min Act: -0.1700
Data Index: 4769074 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.8715. Min Act: -0.1700
Data Index: 4272258 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.8715. Min Act: -0.1700
Data Index: 4222516 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.8715. Min Act: -0.1700
Data Index: 3024728 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2777. Min Range: -5.2777
Max Act: 4.8715. Min Act: -0.1700
Data Index: 935854 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19