Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8761. Min Range: -8.8761
Max Act: 8.8761. Min Act: -0.1700
Data Index: 8606949 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8761. Min Range: -8.8761
Max Act: 8.5636. Min Act: -0.1700
Data Index: 8326131 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8761. Min Range: -8.8761
Max Act: 8.3761. Min Act: -0.1700
Data Index: 3867089 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.9073. Min Act: -0.1700
Data Index: 372485 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.8136. Min Act: -0.1700
Data Index: 8485685 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.7198. Min Act: -0.1700
Data Index: 6797866 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.7198. Min Act: -0.1700
Data Index: 3682396 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.7198. Min Act: -0.1700
Data Index: 5051370 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.6573. Min Act: -0.1700
Data Index: 4824549 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.6573. Min Act: -0.1700
Data Index: 661146 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.5636. Min Act: -0.1700
Data Index: 7967798 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.5948. Min Act: -0.1700
Data Index: 7292559 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.5636. Min Act: -0.1700
Data Index: 489122 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.5323. Min Act: -0.1700
Data Index: 3752591 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.5636. Min Act: -0.1700
Data Index: 7847397 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.5011. Min Act: -0.1700
Data Index: 2433884 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.4698. Min Act: -0.1700
Data Index: 4748626 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.4698. Min Act: -0.1700
Data Index: 4926110 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.4698. Min Act: -0.1700
Data Index: 8794392 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8761. Min Range: -8.8761
Max Act: 7.4386. Min Act: -0.1700
Data Index: 1522432 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19