Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5792 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.6720. Min Act: -0.1700
Data Index: 8761274 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.6095. Min Act: -0.1700
Data Index: 6607641 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4845. Min Act: -0.1700
Data Index: 4138032 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.5470. Min Act: -0.1700
Data Index: 5740304 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4845. Min Act: -0.1700
Data Index: 5399718 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4845. Min Act: -0.1700
Data Index: 3339186 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4845. Min Act: -0.1700
Data Index: 904920 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4845. Min Act: -0.1700
Data Index: 2594906 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.3595. Min Act: -0.1700
Data Index: 2334181 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4220. Min Act: -0.1700
Data Index: 8420041 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4220. Min Act: -0.1700
Data Index: 2908726 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4220. Min Act: -0.1700
Data Index: 5210366 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4220. Min Act: -0.1700
Data Index: 6709480 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.3595. Min Act: -0.1700
Data Index: 540399 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.3595. Min Act: -0.1700
Data Index: 5646853 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.3595. Min Act: -0.1700
Data Index: 8546809 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.4220. Min Act: -0.1700
Data Index: 7377210 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.2970. Min Act: -0.1700
Data Index: 1002858 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.2970. Min Act: -0.1700
Data Index: 2576778 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6720. Min Range: -10.6720
Max Act: 10.2970. Min Act: -0.1700
Data Index: 6904835 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19