Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0637. Min Range: -8.0637
Max Act: 8.0637. Min Act: -0.1700
Data Index: 790714 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.6887. Min Act: -0.1700
Data Index: 8056473 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.5012. Min Act: -0.1700
Data Index: 1498670 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.4074. Min Act: -0.1700
Data Index: 7642573 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.3137. Min Act: -0.1700
Data Index: 108339 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.1887. Min Act: -0.1700
Data Index: 3432543 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.1574. Min Act: -0.1700
Data Index: 5855159 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.1574. Min Act: -0.1700
Data Index: 1494069 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.1262. Min Act: -0.1700
Data Index: 5041461 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0949. Min Act: -0.1700
Data Index: 4202892 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0949. Min Act: -0.1700
Data Index: 3697533 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0949. Min Act: -0.1700
Data Index: 2237205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0637. Min Act: -0.1700
Data Index: 2370501 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0637. Min Act: -0.1700
Data Index: 7833118 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0324. Min Act: -0.1700
Data Index: 5553161 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0637. Min Act: -0.1700
Data Index: 6033815 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0324. Min Act: -0.1700
Data Index: 8297145 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0324. Min Act: -0.1700
Data Index: 7041309 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0012. Min Act: -0.1700
Data Index: 6627324 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0637. Min Range: -8.0637
Max Act: 7.0324. Min Act: -0.1700
Data Index: 2583262 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19