Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1989 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1065. Min Range: -6.1065
Max Act: 6.1065. Min Act: -0.1700
Data Index: 2267055 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1065. Min Range: -6.1065
Max Act: 6.0752. Min Act: -0.1700
Data Index: 7364457 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1065. Min Range: -6.1065
Max Act: 6.0127. Min Act: -0.1700
Data Index: 3239581 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1065. Min Range: -6.1065
Max Act: 6.0127. Min Act: -0.1700
Data Index: 6008927 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1065. Min Range: -6.1065
Max Act: 6.0127. Min Act: -0.1700
Data Index: 5296972 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.9502. Min Act: -0.1700
Data Index: 6620157 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.9502. Min Act: -0.1700
Data Index: 3769665 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.8252. Min Act: -0.1700
Data Index: 1266932 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.8565. Min Act: -0.1700
Data Index: 2061040 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.8565. Min Act: -0.1700
Data Index: 7623958 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.8252. Min Act: -0.1700
Data Index: 401553 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.8252. Min Act: -0.1700
Data Index: 8064854 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.7940. Min Act: -0.1700
Data Index: 3725590 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.7627. Min Act: -0.1700
Data Index: 1540176 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.7002. Min Act: -0.1700
Data Index: 2274690 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.7315. Min Act: -0.1700
Data Index: 1693219 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.7315. Min Act: -0.1700
Data Index: 105890 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.7002. Min Act: -0.1700
Data Index: 8815667 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.6690. Min Act: -0.1700
Data Index: 4169228 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1065. Min Range: -6.1065
Max Act: 5.6690. Min Act: -0.1700
Data Index: 1780117 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19