Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.9852. Min Act: -0.1700
Data Index: 6528915 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.8914. Min Act: -0.1700
Data Index: 6155618 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.8602. Min Act: -0.1700
Data Index: 7630865 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.7977. Min Act: -0.1700
Data Index: 6782539 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.7977. Min Act: -0.1700
Data Index: 2610969 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.7352. Min Act: -0.1700
Data Index: 919102 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.7352. Min Act: -0.1700
Data Index: 1685466 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.6414. Min Act: -0.1700
Data Index: 1429200 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.6102. Min Act: -0.1700
Data Index: 6869671 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.5789. Min Act: -0.1700
Data Index: 4730471 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.5477. Min Act: -0.1700
Data Index: 7710636 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.5477. Min Act: -0.1700
Data Index: 3529537 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.5477. Min Act: -0.1700
Data Index: 6213698 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.5164. Min Act: -0.1700
Data Index: 2545308 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.4852. Min Act: -0.1700
Data Index: 3610928 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.4852. Min Act: -0.1700
Data Index: 8112149 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.4539. Min Act: -0.1700
Data Index: 1595854 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.4227. Min Act: -0.1700
Data Index: 7859332 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.4539. Min Act: -0.1700
Data Index: 4637979 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9852. Min Range: -5.9852
Max Act: 5.4539. Min Act: -0.1700
Data Index: 3689598 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19