Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.7517. Min Act: -0.1700
Data Index: 5861743 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.6267. Min Act: -0.1700
Data Index: 2902673 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.5330. Min Act: -0.1700
Data Index: 4786487 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.4392. Min Act: -0.1700
Data Index: 1573579 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.4080. Min Act: -0.1700
Data Index: 5168075 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.3767. Min Act: -0.1700
Data Index: 4772906 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.3455. Min Act: -0.1700
Data Index: 8680302 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.3455. Min Act: -0.1700
Data Index: 399766 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.3142. Min Act: -0.1700
Data Index: 5894070 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.2830. Min Act: -0.1700
Data Index: 3623275 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.2205. Min Act: -0.1700
Data Index: 4183343 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1580. Min Act: -0.1700
Data Index: 1558510 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1580. Min Act: -0.1700
Data Index: 3582532 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1892. Min Act: -0.1700
Data Index: 8137830 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1892. Min Act: -0.1700
Data Index: 6637167 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1580. Min Act: -0.1700
Data Index: 1255414 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1892. Min Act: -0.1700
Data Index: 3081564 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1580. Min Act: -0.1700
Data Index: 468042 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1580. Min Act: -0.1700
Data Index: 994966 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7517. Min Range: -5.7517
Max Act: 5.1267. Min Act: -0.1700
Data Index: 6412459 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19