Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.6665. Min Act: -0.1700
Data Index: 2119076 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.6040. Min Act: -0.1700
Data Index: 8567588 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.4478. Min Act: -0.1700
Data Index: 8577203 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3540. Min Act: -0.1700
Data Index: 6245437 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3228. Min Act: -0.1700
Data Index: 8440810 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.3228. Min Act: -0.1700
Data Index: 3839267 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.1665. Min Act: -0.1700
Data Index: 5038561 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.1353. Min Act: -0.1700
Data Index: 4758886 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.1040. Min Act: -0.1700
Data Index: 2042680 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.0728. Min Act: -0.1700
Data Index: 8609967 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6665. Min Range: -6.6665
Max Act: 6.0415. Min Act: -0.1700
Data Index: 1256609 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.9790. Min Act: -0.1700
Data Index: 6953760 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.9478. Min Act: -0.1700
Data Index: 4032426 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.9478. Min Act: -0.1700
Data Index: 217602 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.8853. Min Act: -0.1700
Data Index: 874128 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.9165. Min Act: -0.1700
Data Index: 2089684 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.8853. Min Act: -0.1700
Data Index: 1098876 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.9165. Min Act: -0.1700
Data Index: 3339570 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.8853. Min Act: -0.1700
Data Index: 3834549 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6665. Min Range: -6.6665
Max Act: 5.8540. Min Act: -0.1700
Data Index: 1041132 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19