Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 718 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.8882. Min Act: -0.1700
Data Index: 4414883 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.6070. Min Act: -0.1700
Data Index: 727491 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.5757. Min Act: -0.1700
Data Index: 6092250 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.5445. Min Act: -0.1700
Data Index: 7975217 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.5132. Min Act: -0.1700
Data Index: 2752954 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.5132. Min Act: -0.1700
Data Index: 3668678 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.4195. Min Act: -0.1700
Data Index: 4374085 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.4195. Min Act: -0.1700
Data Index: 6879228 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.3570. Min Act: -0.1700
Data Index: 3162286 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.3570. Min Act: -0.1700
Data Index: 2140810 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.3257. Min Act: -0.1700
Data Index: 7820966 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.3257. Min Act: -0.1700
Data Index: 8392388 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.2945. Min Act: -0.1700
Data Index: 4353889 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.2320. Min Act: -0.1700
Data Index: 7608089 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.2632. Min Act: -0.1700
Data Index: 3304628 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.2632. Min Act: -0.1700
Data Index: 3416572 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.2320. Min Act: -0.1700
Data Index: 7482065 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.2320. Min Act: -0.1700
Data Index: 5751310 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.2320. Min Act: -0.1700
Data Index: 5832243 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8882. Min Range: -6.8882
Max Act: 6.2320. Min Act: -0.1700
Data Index: 8684853 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19