Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.9415. Min Act: -0.1700
Data Index: 6081597 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.8165. Min Act: -0.1700
Data Index: 918215 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.6290. Min Act: -0.1700
Data Index: 908908 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.5665. Min Act: -0.1700
Data Index: 4267479 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.6290. Min Act: -0.1700
Data Index: 1728904 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.5665. Min Act: -0.1700
Data Index: 5555812 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.5665. Min Act: -0.1700
Data Index: 483586 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.5352. Min Act: -0.1700
Data Index: 1037978 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.5352. Min Act: -0.1700
Data Index: 949243 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.5040. Min Act: -0.1700
Data Index: 1682426 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.4415. Min Act: -0.1700
Data Index: 6882327 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.4415. Min Act: -0.1700
Data Index: 5050485 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.4102. Min Act: -0.1700
Data Index: 6446533 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.3790. Min Act: -0.1700
Data Index: 1531098 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.4102. Min Act: -0.1700
Data Index: 7975501 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.3790. Min Act: -0.1700
Data Index: 4973803 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.3165. Min Act: -0.1700
Data Index: 1356159 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.3165. Min Act: -0.1700
Data Index: 7468936 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.3165. Min Act: -0.1700
Data Index: 1981589 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9415. Min Range: -7.9415
Max Act: 7.2852. Min Act: -0.1700
Data Index: 568740 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19