Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2139 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.2845. Min Act: -0.1700
Data Index: 4592891 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.2220. Min Act: -0.1700
Data Index: 6214157 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.1282. Min Act: -0.1700
Data Index: 4796865 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.1282. Min Act: -0.1700
Data Index: 6901055 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.1282. Min Act: -0.1700
Data Index: 7583231 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.0657. Min Act: -0.1700
Data Index: 7282505 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.0032. Min Act: -0.1700
Data Index: 6042191 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.0032. Min Act: -0.1700
Data Index: 300811 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.9720. Min Act: -0.1700
Data Index: 5960916 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.9720. Min Act: -0.1700
Data Index: 8285648 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2845. Min Range: -4.2845
Max Act: 4.0032. Min Act: -0.1700
Data Index: 1928008 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.9407. Min Act: -0.1700
Data Index: 3863874 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.9094. Min Act: -0.1700
Data Index: 1964979 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.9407. Min Act: -0.1700
Data Index: 5783957 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.9094. Min Act: -0.1700
Data Index: 998820 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.9094. Min Act: -0.1700
Data Index: 951889 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.8782. Min Act: -0.1700
Data Index: 5191886 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.9094. Min Act: -0.1700
Data Index: 4047832 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.8782. Min Act: -0.1700
Data Index: 5712117 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2845. Min Range: -4.2845
Max Act: 3.8782. Min Act: -0.1700
Data Index: 1533443 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19