Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.8204. Min Act: -0.1700
Data Index: 640302 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.8204. Min Act: -0.1700
Data Index: 8223431 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6954. Min Act: -0.1700
Data Index: 5047632 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6642. Min Act: -0.1700
Data Index: 2688240 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6017. Min Act: -0.1700
Data Index: 649661 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6017. Min Act: -0.1700
Data Index: 7045492 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6017. Min Act: -0.1700
Data Index: 8040556 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6017. Min Act: -0.1700
Data Index: 4279567 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5392. Min Act: -0.1700
Data Index: 2931357 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5392. Min Act: -0.1700
Data Index: 1348087 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5392. Min Act: -0.1700
Data Index: 4991047 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5079. Min Act: -0.1700
Data Index: 5305161 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4767. Min Act: -0.1700
Data Index: 7204908 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4767. Min Act: -0.1700
Data Index: 3661784 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4767. Min Act: -0.1700
Data Index: 1328530 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4767. Min Act: -0.1700
Data Index: 1584468 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4767. Min Act: -0.1700
Data Index: 4904797 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5079. Min Act: -0.1700
Data Index: 3870248 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4767. Min Act: -0.1700
Data Index: 4728868 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4454. Min Act: -0.1700
Data Index: 2657562 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19