Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5454 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.5782. Min Act: -0.1700
Data Index: 2921969 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.5298. Min Act: -0.1700
Data Index: 2578329 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.4812. Min Act: -0.1700
Data Index: 3437760 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.4488. Min Act: -0.1700
Data Index: 1501145 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.4488. Min Act: -0.1700
Data Index: 3934580 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.4650. Min Act: -0.1700
Data Index: 6166237 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.4162. Min Act: -0.1700
Data Index: 5721364 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3836. Min Act: -0.1700
Data Index: 7855096 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3836. Min Act: -0.1700
Data Index: 7927667 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3672. Min Act: -0.1700
Data Index: 6975663 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3672. Min Act: -0.1700
Data Index: 2733004 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3344. Min Act: -0.1700
Data Index: 473799 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3508. Min Act: -0.1700
Data Index: 1650113 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3508. Min Act: -0.1700
Data Index: 3567425 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3344. Min Act: -0.1700
Data Index: 5821081 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3180. Min Act: -0.1700
Data Index: 2562307 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3344. Min Act: -0.1700
Data Index: 2356730 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3344. Min Act: -0.1700
Data Index: 5780267 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3344. Min Act: -0.1700
Data Index: 2311462 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5782. Min Range: -2.5782
Max Act: 2.3344. Min Act: -0.1700
Data Index: 6111887 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19