Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1817. Min Act: -0.1700
Data Index: 2886702 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1817. Min Act: -0.1700
Data Index: 2313287 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1502. Min Act: -0.1700
Data Index: 2013835 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1659. Min Act: -0.1700
Data Index: 3194450 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1502. Min Act: -0.1700
Data Index: 6817266 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1187. Min Act: -0.1700
Data Index: 5607324 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1344. Min Act: -0.1700
Data Index: 4697338 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1187. Min Act: -0.1700
Data Index: 3556763 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1029. Min Act: -0.1700
Data Index: 8829399 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0714. Min Act: -0.1700
Data Index: 2008702 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.1029. Min Act: -0.1700
Data Index: 7816488 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0714. Min Act: -0.1700
Data Index: 7572035 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0872. Min Act: -0.1700
Data Index: 3784267 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0714. Min Act: -0.1700
Data Index: 3837057 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0714. Min Act: -0.1700
Data Index: 4697997 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0714. Min Act: -0.1700
Data Index: 2583618 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0714. Min Act: -0.1700
Data Index: 3277149 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0556. Min Act: -0.1700
Data Index: 8097592 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0556. Min Act: -0.1700
Data Index: 5688016 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1817. Min Range: -3.1817
Max Act: 3.0398. Min Act: -0.1700
Data Index: 5543706 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19