Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.2948. Min Act: -0.1700
Data Index: 3085579 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.2772. Min Act: -0.1698
Data Index: 4822335 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.2243. Min Act: -0.1700
Data Index: 7559890 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.2067. Min Act: -0.1695
Data Index: 4242212 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1891. Min Act: -0.1700
Data Index: 5507629 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.2243. Min Act: -0.1700
Data Index: 4063895 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1715. Min Act: -0.1700
Data Index: 1431200 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1891. Min Act: -0.1700
Data Index: 8618798 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1715. Min Act: -0.1700
Data Index: 2560069 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1891. Min Act: -0.1700
Data Index: 4655856 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1539. Min Act: -0.1695
Data Index: 6552519 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1539. Min Act: -0.1699
Data Index: 700307 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1715. Min Act: -0.1699
Data Index: 6209621 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1363. Min Act: -0.1700
Data Index: 6808909 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1539. Min Act: -0.1700
Data Index: 6380584 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1363. Min Act: -0.1696
Data Index: 7428566 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1013. Min Act: -0.1700
Data Index: 2578872 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1013. Min Act: -0.1700
Data Index: 4707007 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1188. Min Act: -0.1699
Data Index: 5140930 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2948. Min Range: -1.2948
Max Act: 1.1013. Min Act: -0.1700
Data Index: 7760 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19