Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.5831. Min Act: -0.1700
Data Index: 7261073 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.4891. Min Act: -0.1700
Data Index: 1294677 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.3637. Min Act: -0.1700
Data Index: 3977084 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.3637. Min Act: -0.1700
Data Index: 3818884 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.3323. Min Act: -0.1700
Data Index: 1923237 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.3323. Min Act: -0.1700
Data Index: 8743913 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.3009. Min Act: -0.1700
Data Index: 4813707 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2852. Min Act: -0.1700
Data Index: 4489538 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2852. Min Act: -0.1700
Data Index: 3460877 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2852. Min Act: -0.1700
Data Index: 1956045 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2538. Min Act: -0.1700
Data Index: 5369287 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2381. Min Act: -0.1700
Data Index: 435464 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2224. Min Act: -0.1700
Data Index: 7329612 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2224. Min Act: -0.1700
Data Index: 3081842 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2067. Min Act: -0.1700
Data Index: 8424564 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2067. Min Act: -0.1700
Data Index: 6402181 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.2067. Min Act: -0.1700
Data Index: 997057 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.1910. Min Act: -0.1700
Data Index: 6501503 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.1752. Min Act: -0.1700
Data Index: 6132817 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5831. Min Range: -3.5831
Max Act: 3.1752. Min Act: -0.1700
Data Index: 2008126 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19