Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.5299. Min Act: -0.1700
Data Index: 1859607 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4651. Min Act: -0.1700
Data Index: 4729346 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4488. Min Act: -0.1700
Data Index: 2359186 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4326. Min Act: -0.1700
Data Index: 1509227 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4488. Min Act: -0.1699
Data Index: 3152966 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4326. Min Act: -0.1700
Data Index: 4852976 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4000. Min Act: -0.1700
Data Index: 1609296 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4163. Min Act: -0.1700
Data Index: 7698788 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4000. Min Act: -0.1700
Data Index: 3704220 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4163. Min Act: -0.1700
Data Index: 5973990 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4163. Min Act: -0.1700
Data Index: 7771198 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4163. Min Act: -0.1700
Data Index: 8184958 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4163. Min Act: -0.1700
Data Index: 1781082 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.3836. Min Act: -0.1700
Data Index: 2221828 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.3836. Min Act: -0.1700
Data Index: 5478117 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.3836. Min Act: -0.1698
Data Index: 8519538 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.3836. Min Act: -0.1700
Data Index: 6991955 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.4000. Min Act: -0.1700
Data Index: 363551 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.3836. Min Act: -0.1700
Data Index: 2155884 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5299. Min Range: -2.5299
Max Act: 2.3836. Min Act: -0.1700
Data Index: 7408757 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19