Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1401 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1714. Min Range: -9.1714
Max Act: 9.1714. Min Act: -0.1700
Data Index: 4638445 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1714. Min Range: -9.1714
Max Act: 9.1714. Min Act: -0.1700
Data Index: 5526099 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1714. Min Range: -9.1714
Max Act: 9.1089. Min Act: -0.1700
Data Index: 7573600 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1714. Min Range: -9.1714
Max Act: 9.1714. Min Act: -0.1700
Data Index: 7557757 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9839. Min Act: -0.1700
Data Index: 7851125 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9839. Min Act: -0.1700
Data Index: 5385172 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9839. Min Act: -0.1700
Data Index: 156217 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9839. Min Act: -0.1700
Data Index: 3566645 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9839. Min Act: -0.1700
Data Index: 7499798 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9839. Min Act: -0.1700
Data Index: 7429489 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9839. Min Act: -0.1700
Data Index: 3720135 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.8589. Min Act: -0.1700
Data Index: 3455971 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9214. Min Act: -0.1700
Data Index: 1311770 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.8589. Min Act: -0.1700
Data Index: 5581526 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.8589. Min Act: -0.1700
Data Index: 3852166 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.8589. Min Act: -0.1700
Data Index: 7111978 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.7964. Min Act: -0.1700
Data Index: 6884449 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.7964. Min Act: -0.1700
Data Index: 819644 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.8589. Min Act: -0.1700
Data Index: 5788317 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1714. Min Range: -9.1714
Max Act: 8.9214. Min Act: -0.1700
Data Index: 4985728 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19