Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.5852. Min Act: -0.1700
Data Index: 2965246 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.5852. Min Act: -0.1700
Data Index: 4519562 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.4290. Min Act: -0.1700
Data Index: 194000 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.4290. Min Act: -0.1700
Data Index: 5908211 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.3665. Min Act: -0.1700
Data Index: 813396 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2727. Min Act: -0.1700
Data Index: 110600 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2727. Min Act: -0.1700
Data Index: 8808339 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2727. Min Act: -0.1700
Data Index: 6395665 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2727. Min Act: -0.1700
Data Index: 6576328 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2727. Min Act: -0.1700
Data Index: 3583779 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2415. Min Act: -0.1700
Data Index: 1715692 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2415. Min Act: -0.1700
Data Index: 395229 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2102. Min Act: -0.1700
Data Index: 1393892 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.1790. Min Act: -0.1700
Data Index: 8753655 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2415. Min Act: -0.1700
Data Index: 8749442 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.2102. Min Act: -0.1700
Data Index: 6950959 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.1790. Min Act: -0.1700
Data Index: 1970576 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.1790. Min Act: -0.1700
Data Index: 128164 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.1790. Min Act: -0.1700
Data Index: 3666029 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5852. Min Range: -6.5852
Max Act: 6.1790. Min Act: -0.1700
Data Index: 4819675 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19