Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.5853. Min Act: -0.1700
Data Index: 2730099 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3665. Min Act: -0.1700
Data Index: 7026405 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3665. Min Act: -0.1700
Data Index: 2010663 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3040. Min Act: -0.1700
Data Index: 6276273 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2728. Min Act: -0.1700
Data Index: 1175464 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2415. Min Act: -0.1700
Data Index: 5410122 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2415. Min Act: -0.1700
Data Index: 925689 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2103. Min Act: -0.1700
Data Index: 180883 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.1790. Min Act: -0.1700
Data Index: 1887525 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.1790. Min Act: -0.1700
Data Index: 1676345 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2103. Min Act: -0.1700
Data Index: 6429666 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.1790. Min Act: -0.1700
Data Index: 4439125 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.1478. Min Act: -0.1700
Data Index: 4961878 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.1478. Min Act: -0.1700
Data Index: 1324232 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.1478. Min Act: -0.1700
Data Index: 1877841 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.1165. Min Act: -0.1700
Data Index: 1607602 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.0852. Min Act: -0.1700
Data Index: 5508815 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.1165. Min Act: -0.1700
Data Index: 5570720 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.0852. Min Act: -0.1700
Data Index: 1935874 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.0852. Min Act: -0.1700
Data Index: 5413048 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19