Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1805. Min Range: -4.1805
Max Act: 4.1805. Min Act: -0.1700
Data Index: 5382790 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.8992. Min Act: -0.1700
Data Index: 2184749 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.8679. Min Act: -0.1700
Data Index: 7281359 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.8679. Min Act: -0.1700
Data Index: 7586803 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.8054. Min Act: -0.1700
Data Index: 618514 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.7741. Min Act: -0.1700
Data Index: 1713425 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.7741. Min Act: -0.1700
Data Index: 3511586 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.7585. Min Act: -0.1700
Data Index: 4434475 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.7428. Min Act: -0.1700
Data Index: 1622515 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.7428. Min Act: -0.1700
Data Index: 94476 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.7116. Min Act: -0.1700
Data Index: 5744941 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.7116. Min Act: -0.1700
Data Index: 1089132 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.7116. Min Act: -0.1700
Data Index: 5234703 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.6803. Min Act: -0.1700
Data Index: 4490362 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.6803. Min Act: -0.1700
Data Index: 2420768 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.6803. Min Act: -0.1700
Data Index: 1786835 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.6490. Min Act: -0.1700
Data Index: 3931726 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.6490. Min Act: -0.1700
Data Index: 8699702 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.6646. Min Act: -0.1700
Data Index: 7692588 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1805. Min Range: -4.1805
Max Act: 3.6646. Min Act: -0.1700
Data Index: 6320885 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19