Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 333 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.6790. Min Act: -0.1700
Data Index: 5924101 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.6165. Min Act: -0.1700
Data Index: 4353673 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.5853. Min Act: -0.1700
Data Index: 4737165 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.4603. Min Act: -0.1700
Data Index: 6251107 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.4290. Min Act: -0.1700
Data Index: 7725678 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.3978. Min Act: -0.1700
Data Index: 7863037 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.3353. Min Act: -0.1700
Data Index: 2934757 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.3665. Min Act: -0.1700
Data Index: 3396189 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.3040. Min Act: -0.1700
Data Index: 5182243 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2728. Min Act: -0.1700
Data Index: 2503329 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2728. Min Act: -0.1700
Data Index: 7476393 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2728. Min Act: -0.1700
Data Index: 7784019 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2415. Min Act: -0.1700
Data Index: 6139413 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2415. Min Act: -0.1700
Data Index: 1043392 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2415. Min Act: -0.1700
Data Index: 8413299 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2415. Min Act: -0.1700
Data Index: 2248266 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2415. Min Act: -0.1700
Data Index: 4294020 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2415. Min Act: -0.1700
Data Index: 8073916 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.2103. Min Act: -0.1700
Data Index: 5893652 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6790. Min Range: -5.6790
Max Act: 5.1790. Min Act: -0.1700
Data Index: 395886 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19