Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0523. Min Range: -8.0523
Max Act: 8.0523. Min Act: -0.1700
Data Index: 6017845 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.6460. Min Act: -0.1700
Data Index: 2272301 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.5210. Min Act: -0.1700
Data Index: 4701018 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.4273. Min Act: -0.1700
Data Index: 6650330 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.3335. Min Act: -0.1700
Data Index: 8279947 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.3023. Min Act: -0.1700
Data Index: 1870012 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.3335. Min Act: -0.1700
Data Index: 8396111 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.2710. Min Act: -0.1700
Data Index: 475621 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.2085. Min Act: -0.1700
Data Index: 8421127 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.2710. Min Act: -0.1700
Data Index: 7274010 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.1773. Min Act: -0.1700
Data Index: 8426590 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.1460. Min Act: -0.1700
Data Index: 5074621 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.0835. Min Act: -0.1700
Data Index: 1121646 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.0210. Min Act: -0.1700
Data Index: 118961 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.0523. Min Act: -0.1700
Data Index: 3335711 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.0210. Min Act: -0.1700
Data Index: 6666245 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0523. Min Range: -8.0523
Max Act: 6.9585. Min Act: -0.1700
Data Index: 8420803 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0523. Min Range: -8.0523
Max Act: 6.9898. Min Act: -0.1700
Data Index: 5156813 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0523. Min Range: -8.0523
Max Act: 6.9898. Min Act: -0.1700
Data Index: 1174770 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0523. Min Range: -8.0523
Max Act: 6.9585. Min Act: -0.1700
Data Index: 4681133 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19