Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.8752. Min Act: -0.1700
Data Index: 385904 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.7815. Min Act: -0.1700
Data Index: 3493786 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.7502. Min Act: -0.1700
Data Index: 1607445 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.6565. Min Act: -0.1700
Data Index: 8443247 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.5940. Min Act: -0.1700
Data Index: 962419 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.5940. Min Act: -0.1700
Data Index: 5213321 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.5940. Min Act: -0.1700
Data Index: 374796 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.5315. Min Act: -0.1700
Data Index: 5544016 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.4690. Min Act: -0.1700
Data Index: 4131590 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.5002. Min Act: -0.1700
Data Index: 1959554 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.3440. Min Act: -0.1700
Data Index: 6125021 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.3127. Min Act: -0.1700
Data Index: 6406598 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.2502. Min Act: -0.1700
Data Index: 3684291 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.2502. Min Act: -0.1700
Data Index: 3493796 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.2502. Min Act: -0.1700
Data Index: 3566940 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.2502. Min Act: -0.1700
Data Index: 6853127 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.2190. Min Act: -0.1700
Data Index: 1539170 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.1877. Min Act: -0.1700
Data Index: 1172687 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.1877. Min Act: -0.1700
Data Index: 8080989 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8752. Min Range: -5.8752
Max Act: 5.1877. Min Act: -0.1700
Data Index: 3570867 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19