Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1289. Min Range: -5.1289
Max Act: 5.1289. Min Act: -0.1700
Data Index: 7090466 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1289. Min Range: -5.1289
Max Act: 5.0977. Min Act: -0.1700
Data Index: 6110787 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1289. Min Range: -5.1289
Max Act: 5.0664. Min Act: -0.1700
Data Index: 1540915 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1289. Min Range: -5.1289
Max Act: 5.0664. Min Act: -0.1700
Data Index: 2037248 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1289. Min Range: -5.1289
Max Act: 5.0664. Min Act: -0.1700
Data Index: 7803712 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1289. Min Range: -5.1289
Max Act: 5.0352. Min Act: -0.1700
Data Index: 2132368 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1289. Min Range: -5.1289
Max Act: 5.0352. Min Act: -0.1700
Data Index: 4472537 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9727. Min Act: -0.1700
Data Index: 3716694 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9727. Min Act: -0.1700
Data Index: 6863008 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1289. Min Range: -5.1289
Max Act: 5.0039. Min Act: -0.1700
Data Index: 3956632 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9727. Min Act: -0.1700
Data Index: 218095 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9727. Min Act: -0.1700
Data Index: 4168154 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9414. Min Act: -0.1700
Data Index: 3631578 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9414. Min Act: -0.1700
Data Index: 1231080 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9414. Min Act: -0.1700
Data Index: 7892377 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9727. Min Act: -0.1700
Data Index: 2390106 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9102. Min Act: -0.1700
Data Index: 2671179 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9102. Min Act: -0.1700
Data Index: 1534391 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9102. Min Act: -0.1700
Data Index: 5055390 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1289. Min Range: -5.1289
Max Act: 4.9102. Min Act: -0.1700
Data Index: 4317452 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19