Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 263 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 5692775 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.8016. Min Act: -0.1700
Data Index: 5165318 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.7391. Min Act: -0.1700
Data Index: 3518109 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.7079. Min Act: -0.1700
Data Index: 5962997 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.6454. Min Act: -0.1700
Data Index: 5914692 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.6766. Min Act: -0.1700
Data Index: 6284900 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.6454. Min Act: -0.1700
Data Index: 5722106 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.6454. Min Act: -0.1700
Data Index: 5349807 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.5829. Min Act: -0.1700
Data Index: 5563390 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.5516. Min Act: -0.1700
Data Index: 3190595 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.5516. Min Act: -0.1700
Data Index: 3975608 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4891. Min Act: -0.1700
Data Index: 6010546 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.5204. Min Act: -0.1700
Data Index: 3835061 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4579. Min Act: -0.1700
Data Index: 2336749 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.5204. Min Act: -0.1700
Data Index: 2147320 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4891. Min Act: -0.1700
Data Index: 1816168 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4891. Min Act: -0.1700
Data Index: 657621 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4891. Min Act: -0.1700
Data Index: 5970196 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4579. Min Act: -0.1700
Data Index: 237279 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8641. Min Range: -6.8641
Max Act: 6.4266. Min Act: -0.1700
Data Index: 4072008 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19