Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1003 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0737. Min Range: -6.0737
Max Act: 6.0737. Min Act: -0.1700
Data Index: 4007805 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.9800. Min Act: -0.1700
Data Index: 3500921 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.9175. Min Act: -0.1700
Data Index: 244281 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.8550. Min Act: -0.1700
Data Index: 6531035 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.8237. Min Act: -0.1700
Data Index: 1377450 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.7612. Min Act: -0.1700
Data Index: 8233691 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.7612. Min Act: -0.1700
Data Index: 93714 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.7612. Min Act: -0.1700
Data Index: 5211783 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6987. Min Act: -0.1700
Data Index: 969118 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6987. Min Act: -0.1700
Data Index: 5145252 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6987. Min Act: -0.1700
Data Index: 7186425 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6987. Min Act: -0.1700
Data Index: 7245370 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6675. Min Act: -0.1700
Data Index: 6887825 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6675. Min Act: -0.1700
Data Index: 1486496 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6362. Min Act: -0.1700
Data Index: 828730 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6050. Min Act: -0.1700
Data Index: 2849601 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6362. Min Act: -0.1700
Data Index: 5557874 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6050. Min Act: -0.1700
Data Index: 3893342 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6050. Min Act: -0.1700
Data Index: 7021401 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0737. Min Range: -6.0737
Max Act: 5.6050. Min Act: -0.1700
Data Index: 3866061 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19