Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1028 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.6297. Min Act: -0.1700
Data Index: 2622654 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.5672. Min Act: -0.1700
Data Index: 1060176 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.5047. Min Act: -0.1700
Data Index: 689608 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.5672. Min Act: -0.1700
Data Index: 2803633 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.4734. Min Act: -0.1700
Data Index: 4528714 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.4734. Min Act: -0.1700
Data Index: 8748124 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.4422. Min Act: -0.1700
Data Index: 6743687 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.4422. Min Act: -0.1700
Data Index: 7865111 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.4422. Min Act: -0.1700
Data Index: 3112069 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3797. Min Act: -0.1700
Data Index: 4528713 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3484. Min Act: -0.1700
Data Index: 1263707 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3172. Min Act: -0.1700
Data Index: 7865105 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3172. Min Act: -0.1700
Data Index: 734903 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3172. Min Act: -0.1700
Data Index: 1041331 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2859. Min Act: -0.1700
Data Index: 6684297 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3172. Min Act: -0.1700
Data Index: 431478 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3172. Min Act: -0.1700
Data Index: 734895 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2859. Min Act: -0.1700
Data Index: 6561538 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2859. Min Act: -0.1700
Data Index: 431479 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2547. Min Act: -0.1700
Data Index: 609770 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19