Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.5891. Min Act: -0.1700
Data Index: 8741230 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.4641. Min Act: -0.1700
Data Index: 382967 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.4016. Min Act: -0.1700
Data Index: 7783988 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2766. Min Act: -0.1700
Data Index: 3430797 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2766. Min Act: -0.1700
Data Index: 8026338 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2766. Min Act: -0.1700
Data Index: 1880062 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2766. Min Act: -0.1700
Data Index: 7503161 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2766. Min Act: -0.1700
Data Index: 246861 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2454. Min Act: -0.1700
Data Index: 5520803 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2454. Min Act: -0.1700
Data Index: 2825558 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2141. Min Act: -0.1700
Data Index: 2312607 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.2454. Min Act: -0.1700
Data Index: 8581677 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.1829. Min Act: -0.1700
Data Index: 8380391 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.1516. Min Act: -0.1700
Data Index: 8629949 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.1829. Min Act: -0.1700
Data Index: 282904 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.1516. Min Act: -0.1700
Data Index: 7018070 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.1516. Min Act: -0.1700
Data Index: 1581369 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.1516. Min Act: -0.1700
Data Index: 4412558 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.1516. Min Act: -0.1700
Data Index: 2834054 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5891. Min Range: -5.5891
Max Act: 5.1516. Min Act: -0.1700
Data Index: 3201202 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19