Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.5641. Min Act: -0.1700
Data Index: 1877753 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.5016. Min Act: -0.1700
Data Index: 6276908 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.4078. Min Act: -0.1700
Data Index: 7318395 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.4078. Min Act: -0.1700
Data Index: 1862107 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.4078. Min Act: -0.1700
Data Index: 284375 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3766. Min Act: -0.1700
Data Index: 5075910 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3766. Min Act: -0.1700
Data Index: 8671600 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.4078. Min Act: -0.1700
Data Index: 4621308 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3453. Min Act: -0.1700
Data Index: 7805593 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3453. Min Act: -0.1700
Data Index: 4984064 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3453. Min Act: -0.1700
Data Index: 5812295 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3453. Min Act: -0.1700
Data Index: 5731041 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3453. Min Act: -0.1700
Data Index: 7579035 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3141. Min Act: -0.1700
Data Index: 4020080 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3141. Min Act: -0.1700
Data Index: 183862 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.3453. Min Act: -0.1700
Data Index: 6143775 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.2828. Min Act: -0.1700
Data Index: 4068342 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.2828. Min Act: -0.1700
Data Index: 5102956 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.2828. Min Act: -0.1700
Data Index: 7555848 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.2203. Min Act: -0.1700
Data Index: 6688283 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19