Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1735 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.8182. Min Act: -0.1700
Data Index: 3929466 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.7245. Min Act: -0.1700
Data Index: 1997426 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.6620. Min Act: -0.1700
Data Index: 4144138 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.6307. Min Act: -0.1700
Data Index: 5559978 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.5682. Min Act: -0.1700
Data Index: 6237749 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.5995. Min Act: -0.1700
Data Index: 5897397 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.5370. Min Act: -0.1700
Data Index: 336486 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.5370. Min Act: -0.1700
Data Index: 8170168 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4745. Min Act: -0.1700
Data Index: 8440027 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4745. Min Act: -0.1700
Data Index: 3901173 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4120. Min Act: -0.1700
Data Index: 8437732 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4745. Min Act: -0.1700
Data Index: 1810542 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4432. Min Act: -0.1700
Data Index: 7823132 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.3807. Min Act: -0.1700
Data Index: 5590442 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4432. Min Act: -0.1700
Data Index: 752905 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.3807. Min Act: -0.1700
Data Index: 3272749 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4120. Min Act: -0.1700
Data Index: 6673061 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4120. Min Act: -0.1700
Data Index: 1629996 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.4120. Min Act: -0.1700
Data Index: 8664557 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8182. Min Range: -4.8182
Max Act: 4.3807. Min Act: -0.1700
Data Index: 4070452 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19