Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0807. Min Range: -10.0807
Max Act: 10.0807. Min Act: -0.1700
Data Index: 322898 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.9557. Min Act: -0.1700
Data Index: 7069690 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.9557. Min Act: -0.1700
Data Index: 8501053 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.8932. Min Act: -0.1700
Data Index: 4902204 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.8932. Min Act: -0.1700
Data Index: 7139694 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.7682. Min Act: -0.1700
Data Index: 2009396 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.7682. Min Act: -0.1700
Data Index: 1340132 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.7682. Min Act: -0.1700
Data Index: 2662949 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.7057. Min Act: -0.1699
Data Index: 2066581 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.6432. Min Act: -0.1700
Data Index: 794837 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.7057. Min Act: -0.1700
Data Index: 206338 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.6432. Min Act: -0.1700
Data Index: 6558088 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.7057. Min Act: -0.1700
Data Index: 8535126 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.5807. Min Act: -0.1700
Data Index: 2703631 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.5807. Min Act: -0.1700
Data Index: 2753432 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.5807. Min Act: -0.1700
Data Index: 2267919 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.5807. Min Act: -0.1700
Data Index: 7385529 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.5182. Min Act: -0.1700
Data Index: 6703657 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.5182. Min Act: -0.1700
Data Index: 2364467 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0807. Min Range: -10.0807
Max Act: 9.5182. Min Act: -0.1700
Data Index: 7000490 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19