Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2556 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.7852. Min Act: -0.1700
Data Index: 6733726 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.4414. Min Act: -0.1700
Data Index: 2625813 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.4102. Min Act: -0.1700
Data Index: 7411117 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.2852. Min Act: -0.1700
Data Index: 1083575 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.2539. Min Act: -0.1700
Data Index: 3251239 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.2227. Min Act: -0.1700
Data Index: 2016722 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.1914. Min Act: -0.1700
Data Index: 5763355 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.1914. Min Act: -0.1700
Data Index: 5831627 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.1602. Min Act: -0.1700
Data Index: 1563852 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.1602. Min Act: -0.1700
Data Index: 1563850 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.1602. Min Act: -0.1700
Data Index: 5763362 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.1289. Min Act: -0.1700
Data Index: 5294154 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.1289. Min Act: -0.1700
Data Index: 1735480 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.1289. Min Act: -0.1700
Data Index: 1448447 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.0664. Min Act: -0.1700
Data Index: 7064328 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.0664. Min Act: -0.1700
Data Index: 2137760 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.0664. Min Act: -0.1700
Data Index: 2029389 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.0352. Min Act: -0.1700
Data Index: 5540050 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7852. Min Range: -7.7852
Max Act: 7.0039. Min Act: -0.1700
Data Index: 7062768 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7852. Min Range: -7.7852
Max Act: 6.9727. Min Act: -0.1700
Data Index: 3001177 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19